| Title: | Diagnostic Test Accuracy Meta-Analysis using Template Model Builder |
|---|---|
| Description: | Fits the hierarchical summary receiver operating characteristic (HSROC) model of Rutter and Gatsonis (2001) <doi:10.1002/sim.942>, the bivariate binomial-normal model of Reitsma et al. (2005) <doi:10.1016/j.jclinepi.2005.02.022>, the threshold-based bivariate time-to-event model of Hoyer et al. (2018) <doi:10.1002/jrsm.1273>, and the latent class extensions of Liu et al. (2015) <doi:10.1111/biom.12264> for diagnostic studies with an imperfect reference standard. Provides subgroup analyses, HSROC meta-regression, likelihood-ratio tests, summary ROC plots, and coupled forest plots. |
| Authors: | Claus Nowak [aut, cre] |
| Maintainer: | Claus Nowak <[email protected]> |
| License: | GPL (>= 2) |
| Version: | 0.1.3.9000 |
| Built: | 2026-10-19 20:22:05 UTC |
| Source: | https://github.com/ebme-uwk/dtametatmb |
This is a synthetic dataset where haemoglobin was measured by a point-of-care device, with laboratory measurement acting as the reference standard. Lower values indicate disease (anaemia).
anaemiaanaemia
A data frame with 81 rows and 11 variables:
Study identifier
Haemoglobin in g/dL
Number of true positives
Number of false negatives
Number of false positives
Number of true negatives
Number of diseased individuals
Number of healthy individuals
Sensitivity
False positive rate
Smaller values indicate disease (=less)
Synthetic dataset.
Compare nested diagnostic test accuracy meta-analysis models using likelihood ratio tests (LRTs).
## S3 method for class 'Reitsma' anova(object, ..., test = "Chisq") ## S3 method for class 'RutterGatsonis' anova(object, ..., test = "Chisq")## S3 method for class 'Reitsma' anova(object, ..., test = "Chisq") ## S3 method for class 'RutterGatsonis' anova(object, ..., test = "Chisq")
object |
A fitted model object. |
... |
Additional fitted model objects to be compared. |
test |
Character string specifying the test to perform. Currently,
only |
These methods compute likelihood ratio statistics from the fitted model log-likelihoods and compare models ordered by increasing numbers of estimated parameters. The test statistic is
where and are the log-likelihoods of two nested
models. Under standard regularity conditions, the statistic follows a
chi-squared distribution with degrees of freedom equal to the difference
in the numbers of estimated parameters.
The models supplied should be nested and fitted to the same dataset. Warnings are issued when models have identical numbers of parameters or when the log-likelihood decreases for a more complex model, suggesting that the nesting assumptions may be violated.
An object of class "anova" inheriting from "data.frame" with
the following columns:
Number of estimated parameters in the model.
Model log-likelihood.
Difference in parameters compared with the previous model.
Likelihood ratio chi-squared statistic.
P-value from the chi-squared test.
The usual chi-squared reference distribution requires appropriate regularity conditions. In particular, these conditions may not hold when the null hypothesis constrains one or more random-effects variance components to zero, because variances are non-negative and zero lies on the boundary of the parameter space.
This issue can arise when comparing Reitsma models that constrain sigma2_A or sigma2_B, or Rutter-Gatsonis models that constrain sigma2_alpha or sigma2_theta. Tests involving multiple variance components constrained to zero may require additional care. In such cases, the asymptotic reference distribution may be a mixture of chi-squared distributions rather than a single chi-squared distribution. The appropriate distribution depends on the model and the constraints being tested.
The implementation uses the ordinary chi-squared reference distribution and does not apply a boundary-adjusted reference distribution. Therefore, the reported p-values may not be appropriately calibrated for tests of variance components on the boundary.
Self, S. G. and Liang, K. Y. (1987). Asymptotic properties of maximum likelihood estimators and likelihood ratio tests under nonstandard conditions. Journal of the American Statistical Association, 82, 605–610.
Stram, D. O. and Lee, J. W. (1994). Variance components testing in the longitudinal mixed effects model. Biometrics, 50, 1171–1177.
This is the anticcp dataset from Nishimura (2007) from a review of anti-cyclic citrullinated peptide antibody (anti-ccp) to diagnose rheumatoid arthritis.
anticcpanticcp
A data frame with 37 rows and 7 variables:
Study identifier
Year of the study
Number of true positives
Number of false positives
Number of false negatives
Number of true negatives
First generation (CCP1) or second generation (CCP2) assay
Nishimura, K. et al. (2007). Meta-analysis: diagnostic accuracy of anti-cyclic citrullinated peptide antibody and rheumatoid factor for rheumatoid arthritis. Annals of Internal Medicine, 146(11), 392-403. doi:10.7326/0003-4819-146-11-200706050-00008
Converts fitted model objects (Reitsma, ReitsmaSubgroup, RutterGatsonis,
RutterGatsonisSubgroup, ReitsmaLCA, ReitsmaSubgroupLCA, RutterGatsonisLCA, and
RutterGatsonisSubgroupLCA) into a format suitable for manual entry
into the Diagnostic Test Accuracy module of Review Manager (RevMan).
as_revman(x, ...) ## S3 method for class 'Reitsma' as_revman(x, ...) ## S3 method for class 'RutterGatsonis' as_revman(x, ...) ## S3 method for class 'ReitsmaSubgroup' as_revman(x, ...) ## S3 method for class 'RutterGatsonisSubgroup' as_revman(x, ...) ## S3 method for class 'ReitsmaLCA' as_revman(x, ...) ## S3 method for class 'RutterGatsonisLCA' as_revman(x, ...) ## S3 method for class 'ReitsmaSubgroupLCA' as_revman(x, ...) ## S3 method for class 'RutterGatsonisSubgroupLCA' as_revman(x, ...) ## S3 method for class 'ReitsmaSubgroupTMB' as_revman(x, ...) ## S3 method for class 'ReitsmaTMB' as_revman(x, ...)as_revman(x, ...) ## S3 method for class 'Reitsma' as_revman(x, ...) ## S3 method for class 'RutterGatsonis' as_revman(x, ...) ## S3 method for class 'ReitsmaSubgroup' as_revman(x, ...) ## S3 method for class 'RutterGatsonisSubgroup' as_revman(x, ...) ## S3 method for class 'ReitsmaLCA' as_revman(x, ...) ## S3 method for class 'RutterGatsonisLCA' as_revman(x, ...) ## S3 method for class 'ReitsmaSubgroupLCA' as_revman(x, ...) ## S3 method for class 'RutterGatsonisSubgroupLCA' as_revman(x, ...) ## S3 method for class 'ReitsmaSubgroupTMB' as_revman(x, ...) ## S3 method for class 'ReitsmaTMB' as_revman(x, ...)
x |
A fitted model object. |
... |
Currently not used. |
A data frame with columns:
Only returned for subgroup model objects.
RevMan model/parameter types.
RevMan parameter name.
Parameter estimate.
The returned table contains the model parameters displayed by RevMan:
E(logitSe)
E(logitSp)
Var(logitSe)
Var(logitSp)
Cov(logits)
Corr(logits)
Lambda
Theta
beta
Var(accuracy)
Var(threshold)
SE(E(logitSe))
SE(E(logitSp))
Cov(Es)
Studies
For Rutter and Gatsonis models SE(E(logitSe)), SE(E(logitSp)), and Cov(Es) are not computed.
Returns the estimated model parameters.
## S3 method for class 'DTAmodel' coef(object, ...) ## S3 method for class 'Reitsma' coef(object, ...) ## S3 method for class 'ReitsmaSubgroup' coef(object, ...) ## S3 method for class 'ReitsmaLCA' coef(object, ...) ## S3 method for class 'ReitsmaSubgroupLCA' coef(object, ...) ## S3 method for class 'ReitsmaSubgroupTMB' coef(object, ...) ## S3 method for class 'ReitsmaTMB' coef(object, ...)## S3 method for class 'DTAmodel' coef(object, ...) ## S3 method for class 'Reitsma' coef(object, ...) ## S3 method for class 'ReitsmaSubgroup' coef(object, ...) ## S3 method for class 'ReitsmaLCA' coef(object, ...) ## S3 method for class 'ReitsmaSubgroupLCA' coef(object, ...) ## S3 method for class 'ReitsmaSubgroupTMB' coef(object, ...) ## S3 method for class 'ReitsmaTMB' coef(object, ...)
object |
A fitted model object. |
... |
Not currently used. |
A named vector of parameter estimates.
For ReitsmaSubgroup models, coef() returns
parameter estimates from the cell-means parameterization rather
than treatment-contrast coefficients.
This is the dementia dataset from Harrison et al. (2015) from a review of the Informant Questionnaire on Cognitive Decline in the Elderly (IQCODE) for the diagnosis of dementia within a secondary care setting.
dementiadementia
A data frame with 13 rows and 17 variables:
Author of the study
Year of the study
Number of true positives
Number of false negatives
Number of false positives
Number of true negatives
Risk of bias: Patient selection
Risk of bias: Index test
Risk of bias: Reference standard
Risk of bias: Flow and timing
Applicability: Patient selection
Applicability: Index test
Applicability: Reference standard
Threshold category
Country category
Informant Questionnaire on Cognitive Decline in the Elderly category
Reference category
The data were taken as provided from the MetaBayesDTA application.
Cerullo, E. et al. (2023). MetaBayesDTA: codeless Bayesian meta-analysis of test accuracy, with or without a gold standard BMC Medical Research Methodology 23(127). doi:10.1186/s12874-023-01910-y
Harrison, J. et al. (2015). Informant Questionnaire on Cognitive Decline in the Elderly (IQCODE) for the diagnosis of dementia within a secondary care setting.. Cochrane Database of Systematic Reviews 3. doi:10.1002/14651858.CD010772.pub2
This is the diabetes dataset from the supplementary material in Hoyer (2018).
diabetesdiabetes
A data frame with 124 rows and 9 variables
Study identifier
Threshold HbA1c used to derive TP, FN, FP, TN
Number of true positives
Number of true negatives
Number of false positives
Number of false negatives
Number of diseased individuals
Number of healthy individuals
Whether the data threshold/row was used in the original publication (1=yes, 0=no)
Hoyer, A., Hirt, S., Kuss, O. (2018). Meta-analysis of full ROC curves using bivariate time-to-event models for interval-censored data. Research Synthesis Methods, 9(1), 62-72. doi:10.1002/jrsm.1273
Functions for fitting diagnostic test accuracy (DTA) meta-analysis models using Template Model Builder (TMB).
Implemented methods
Reitsma model
Rutter-Gatsonis HSROC model
Hoyer multiple-threshold model
Latent class analysis for studies with an imperfect reference standard
Main workflow
fitReitsma() -> print() -> summary() -> plot() -> forest()
fitReitsmaTMB() -> print() -> summary() -> plot() -> forest()
fitReitsmaSubgroup() -> print() -> summary() -> plot() -> forest()
fitReitsmaSubgroupTMB() -> print() -> summary() -> plot() -> forest()
fitRutterGatsonis() -> print() -> summary() -> plot() -> forest()
fitRutterGatsonisSubgroup() -> print() -> summary() -> plot() -> forest()
fitHoyer() -> print() -> summary() -> plot() -> forest()
fitReitsmaLCA() -> print() -> summary() -> plot() -> forest()
fitReitsmaSubgroupLCA() -> print() -> summary() -> plot() -> forest()
fitRutterGatsonisLCA() -> print() -> summary() -> plot() -> forest()
fitRutterGatsonisSubgroupLCA() -> print() -> summary() -> plot() -> forest()
Included datasets
anaemia
anticcp
diabetes
dementia
FENO
pap
RF
schuetz
tub
See the package vignettes for worked examples and model descriptions.
Maintainer: Claus Nowak [email protected]
Authors:
Claus Nowak [email protected]
Useful links:
This is the FENO dataset from Schneider (2017) from a review of fractional exhaled nitric oxide (FeNO) for diagnosis of asthma.
FENOFENO
A data frame with 150 rows and 7 variables:
Study identifier
Study identifier (numeric)
Threshold for FeNO measured in ppb
Number of true positives
Number of false negatives
Number of false positives
Number of true negatives
The data are reproduced from the original source and the supplementary material accompanying the Cochrane Handbook. However, the study 'Schneider 2013' contains inconsistent diseased counts (TP + FN). To illustrate the Hoyer analysis in the vignette, we modify the TP counts in rows 118–120 from 39 to 38. Other corrections restoring internal consistency are also conceivable.
Schneider, A. et al. (2017). A novel statistical model for analyzing data of a systematic review generates optimal cutoff values for fractional exhaled nitric oxide for asthma diagnosis. Journal of Clinical Epidemiology, 92, 69-78. doi:10.1016/j.jclinepi.2017.09.001
This is a high-level wrapper that performs the full workflow for fitting the Hoyer AFT model:
Restructuring of threshold-based data into interval format
Estimation of initial parameter values
Model fitting via likelihood maximization
The input data must contain cumulative counts for true positives, false positives, false negatives, and true negatives at multiple thresholds within each study.
fitHoyer( data, TP, FP, FN, TN, study, threshold, smallest, largest, testdirection = c("greater", "less"), eval_threshold = NULL, conflevel = 0.95, dist = "loglogistic", verbose = FALSE, ... )fitHoyer( data, TP, FP, FN, TN, study, threshold, smallest, largest, testdirection = c("greater", "less"), eval_threshold = NULL, conflevel = 0.95, dist = "loglogistic", verbose = FALSE, ... )
data |
A data.frame containing study-level data. |
TP |
True positives (column name). |
FP |
False positives (column name). |
FN |
False negatives (column name). |
TN |
True negatives (column name). |
study |
Study identifier (column name). |
threshold |
The observed threshold value (column name). Must be positive and strictly increasing within each study. |
smallest |
Positive lower bound used to define the
leftmost interval. Must be smaller than minimum |
largest |
Positive upper bound used to define the
rightmost interval. Must be greater than maximum |
testdirection |
Direction of the test. Enter |
eval_threshold |
Optional numeric value or vector specifying the
prediction grid threshold(s) at which sensitivity and specificity
should be evaluated. If |
conflevel |
Confidence level for confidence intervals for sensitivities
and specificities at the chosen thresholds. Defaults to |
dist |
Character string specifying the parametric distribution
for the AFT model. One of |
verbose |
Whether TMB optimization output should be printed (default: FALSE). |
... |
Additional arguments (unused). |
Fits the threshold-based bivariate accelerated failure time (AFT) model for diagnostic test accuracy (DTA) meta-analysis as described by Hoyer et al. (2018). The model is estimated using interval-censored likelihoods via Template Model Builder (TMB).
The function internally calls:
restructure_data to convert cumulative counts into
interval-censored data
initHoyerAFT to estimate starting values
fitHoyerAFT to fit the model
Missing values in the input data are removed prior to analysis. A message is issued listing the affected studies.
An object of class "HoyerAFT" as returned by
fitHoyerAFT, containing:
Processed original data
Interval-formatted data
Optimization output
TMB report object
Summary of reported parameters
Sensitivity and specificity estimates
Requires a compiled TMB model named "Hoyer".
Hoyer, A., Hirt, S., Kuss, O. (2018). Meta-analysis of full ROC curves using bivariate time-to-event models for interval-censored data. Research Synthesis Methods, 9(1), 62-72. doi:10.1002/jrsm.1273
data("diabetes") fit <- fitHoyer( data = diabetes, TP = TP, FP = FP, FN = FN, TN = TN, study = study, threshold = threshold, testdirection = "greater", smallest = 2, largest = 10 ) summary(fit)data("diabetes") fit <- fitHoyer( data = diabetes, TP = TP, FP = FP, FN = FN, TN = TN, study = study, threshold = threshold, testdirection = "greater", smallest = 2, largest = 10 ) summary(fit)
Fits a bivariate accelerated failure time (AFT) model for diagnostic test accuracy (DTA) data using interval-censored likelihoods as described in Hoyer et al. (2018). The model is estimated using Template Model Builder (TMB) with study-specific random effects.
fitHoyerAFT( data, init, conflevel = 0.95, eval_threshold = NULL, verbose = FALSE )fitHoyerAFT( data, init, conflevel = 0.95, eval_threshold = NULL, verbose = FALSE )
data |
A list as produced by
|
init |
A data frame of initial parameter values as produced by
|
conflevel |
Confidence level for confidence intervals for sensitivities
and specificities at the chosen thresholds. Defaults to |
eval_threshold |
Optional numeric value or vector specifying the
prediction grid threshold(s) at which sensitivity and specificity
should be evaluated. If |
verbose |
Whether TMB optimization output should be printed (default: FALSE). |
The model reports logit-survival quantities, which correspond to sensitivity
and false positive rate for testdirection = "greater", and to false
negative rate and specificity for testdirection = "less".
Model fitting is performed using nlminb, and uncertainty
estimates are obtained via TMB::sdreport. Parameter
transformations include log-scale parameters and Fisher's Z-transform
for correlations.
An object of class "HoyerAFT" containing:
Processed original data
Interval-formatted data
Optimization output from nlminb
TMB report object from sdreport
Summary of reported parameters
Distribution code used in the model
Sensitivities and specificities at the chosen thresholds
Requires a compiled TMB model named "Hoyer".
Hoyer, A., Hirt, S., Kuss, O. (2018). Meta-analysis of full ROC curves using bivariate time-to-event models for interval-censored data. Research Synthesis Methods, 9(1), 62-72. doi:10.1002/jrsm.1273
data("diabetes") res <- restructure_data( data = diabetes, TP = TP, FP = FP, FN = FN, TN = TN, threshold = threshold, study = study, smallest = 2, largest = 10 ) init <- initHoyerAFT(res$restructured) fit <- fitHoyerAFT(res, init) summary(fit)data("diabetes") res <- restructure_data( data = diabetes, TP = TP, FP = FP, FN = FN, TN = TN, threshold = threshold, study = study, smallest = 2, largest = 10 ) init <- initHoyerAFT(res$restructured) fit <- fitHoyerAFT(res, init) summary(fit)
Fits the Reitsma bivariate random-effects model for diagnostic test accuracy (DTA)
meta-analysis using a binomial-normal likelihood via glmmTMB.
fitReitsma(data, TP, FP, FN, TN, study, constrain = NULL, conflevel = 0.95)fitReitsma(data, TP, FP, FN, TN, study, constrain = NULL, conflevel = 0.95)
data |
A data.frame containing study-level data. |
TP |
True positives (column name). |
FP |
False positives (column name). |
FN |
False negatives (column name). |
TN |
True negatives (column name). |
study |
Study identifier (column name). |
constrain |
Optional character string specifying a simplified covariance structure for the Reitsma model. This can be useful for sparse data, small meta-analyses, or for reproducing simplified bivariate models described in the Cochrane Handbook for Diagnostic Test Accuracy Reviews. Allowed values are:
|
conflevel |
Confidence level for confidence intervals. Default is 0.95. |
A list of class "Reitsma" with components:
data: the original data set with derived quantities
glmmTMB: fitted model object.
estimates: parameter estimates with SE.
vcov: variance-covariance matrix.
sensspec: sensitivity and specificity estimates.
LRDOR: Diagnostic odds ratio and likelihood ratios.
RutterGatsonis_recovered: Recovered parameters in the Rutter-Gatsonis (HSROC) parameterization.
constrain: Random effects parameters fixed at zero.
Reitsma, J. B., et al. (2005). Bivariate analysis of sensitivity and specificity produces informative summary measures in diagnostic reviews. Journal of Clinical Epidemiology, 58(10), 982–990. doi:10.1016/j.jclinepi.2005.02.022
Rutter, C. M., & Gatsonis, C. A. (2001). A hierarchical regression approach to meta-analysis of diagnostic test accuracy evaluations. Statistics in Medicine, 20(19), 2865–2884. doi:10.1002/sim.942
Harbord, R. M., Deeks, J. J., Egger, M., Whiting, P., & Sterne, J. A. C. (2007). A unification of models for meta-analysis of diagnostic accuracy studies. Biostatistics, 8(2), 239–251. doi:10.1093/biostatistics/kxl004
data("anticcp") fit <- fitReitsma( data = anticcp, TP = TP, FP = FP, FN = FN, TN = TN, study = study ) summary(fit)data("anticcp") fit <- fitReitsma( data = anticcp, TP = TP, FP = FP, FN = FN, TN = TN, study = study ) summary(fit)
Fits the Reitsma latent class model for diagnostic test accuracy (DTA), allowing for an imperfect reference standard under conditional independence.
fitReitsmaLCA( data, y11, y10, y01, y00, study, conflevel = 0.95, constrain = NULL, verbose = FALSE )fitReitsmaLCA( data, y11, y10, y01, y00, study, conflevel = 0.95, constrain = NULL, verbose = FALSE )
data |
A data.frame containing study-level data. |
y11 |
Number testing positive with both index and reference tests (column name). |
y10 |
Number testing positive with index test but negative with reference test (column name). |
y01 |
Number testing negative with index test but positive with reference test (column name). |
y00 |
Number testing negative with both index and reference tests (column name). |
study |
Study identifier (column name). |
conflevel |
Confidence level for confidence intervals. Default is 0.95. |
constrain |
Optional character string specifying a simplified covariance structure for the index test of the Reitsma LCA model. Allowed values are:
|
verbose |
Whether TMB optimization output should be printed (default: FALSE). |
A list of class "ReitsmaLCA" with components:
data: the original data set with derived quantities.
fit: Optimization result from nlminb.
sdreport: TMB standard report.
sdreport2: Summary of reported parameters.
vcov: variance-covariance matrix of reported parameters.
sensspec: sensitivity and specificity estimates.
prevref: Estimated (average) prevalence and reference standard sensitivity/specificity with confidence intervals.
LRDOR: Diagnostic odds ratio and likelihood ratios.
RutterGatsonis_recovered: Recovered parameters in the Rutter-Gatsonis (HSROC) parameterization.
constrain: Random effects parameters fixed at zero.
Liu, Y., Chen, Y., & Chu, H. (2015). A unification of models for meta-analysis of diagnostic accuracy studies without a gold standard. Biometrics, 71(2), 538-547. doi:10.1111/biom.12264
Reitsma, J. B., et al. (2005). Bivariate analysis of sensitivity and specificity produces informative summary measures in diagnostic reviews. Journal of Clinical Epidemiology, 58(10), 982–990. doi:10.1016/j.jclinepi.2005.02.022
Rutter, C. M., & Gatsonis, C. A. (2001). A hierarchical regression approach to meta-analysis of diagnostic test accuracy evaluations. Statistics in Medicine, 20(19), 2865–2884. doi:10.1002/sim.942
Harbord, R. M., Deeks, J. J., Egger, M., Whiting, P., & Sterne, J. A. C. (2007). A unification of models for meta-analysis of diagnostic accuracy studies. Biostatistics, 8(2), 239–251. doi:10.1093/biostatistics/kxl004
data("anticcp") fit <- fitReitsmaLCA( data = anticcp, y11 = TP, y10 = FP, y01 = FN, y00 = TN, study = study ) fit summary(fit)data("anticcp") fit <- fitReitsmaLCA( data = anticcp, y11 = TP, y10 = FP, y01 = FN, y00 = TN, study = study ) fit summary(fit)
Fits the Reitsma bivariate random-effects model with a single categorical covariate
for diagnostic test accuracy (DTA) meta-analysis using a binomial-normal
likelihood via glmmTMB. The model is fitted twice, once using treatment-contrast
coding with a reference subgroup and once using the cell-means parameterization.
fitReitsmaSubgroup( data, TP, FP, FN, TN, study, subgroup, constrain = NULL, sensspec_constrain = NULL, variances = c("common", "unequal"), conflevel = 0.95 )fitReitsmaSubgroup( data, TP, FP, FN, TN, study, subgroup, constrain = NULL, sensspec_constrain = NULL, variances = c("common", "unequal"), conflevel = 0.95 )
data |
A data.frame containing study-level data. |
TP |
True positives (column name). |
FP |
False positives (column name). |
FN |
False negatives (column name). |
TN |
True negatives (column name). |
study |
Study identifier (column name). |
subgroup |
A single categorical study-level subgroup variable (column name). |
constrain |
Optional character string specifying a simplified covariance structure for the Reitsma model. This can be useful for sparse data, small meta-analyses, or for reproducing simplified bivariate models described in the Cochrane Handbook for Diagnostic Test Accuracy Reviews. Allowed values are:
These random-effects simplifications are currently only available for
|
sensspec_constrain |
Optional character vector specifying restrictions on subgroup-specific logit-sensitivity and/or logit-specificity parameters. This can be useful for testing whether subgroup differences are present in sensitivity, specificity, or both. Allowed values are:
Both constraints may be specified simultaneously, e.g.
If |
variances |
Whether the between-study random-effects variance-covariance
matrix should be assumed to be |
conflevel |
Confidence level for confidence intervals. Default is 0.95. |
A list of class "ReitsmaSubgroup" with components:
data: the original data set with derived quantities.
glmmTMB_mu: fitted model object with cell means parameterization.
estimates_mu: parameter estimates with SE with cell means parameterization.
vcov_mu: variance-covariance matrix with cell means parameterization.
sensspec: sensitivity and specificity estimates.
glmmTMB_nu: fitted model object with dummy/reference-cell parameterization.
estimates_nu: parameter estimates with SE with dummy/reference-cell parameterization.
vcov_nu: variance-covariance matrix with dummy/reference-cell parameterization.
LRDOR: Diagnostic odds ratios and likelihood ratios.
RutterGatsonis_recovered: Recovered parameters in the Rutter-Gatsonis (HSROC) parameterization.
subgroups: The subgroup levels used in the model fit.
constrain: Random effects parameters fixed at zero.
sensspec_constrain: Whether sensitivities/specificities are assumed common across subgroups.
variances: Variance structure used in the fitted model.
Reitsma, J. B., et al. (2005). Bivariate analysis of sensitivity and specificity produces informative summary measures in diagnostic reviews. Journal of Clinical Epidemiology, 58(10), 982–990. doi:10.1016/j.jclinepi.2005.02.022
Rutter, C. M., & Gatsonis, C. A. (2001). A hierarchical regression approach to meta-analysis of diagnostic test accuracy evaluations. Statistics in Medicine, 20(19), 2865–2884. doi:10.1002/sim.942
Harbord, R. M., Deeks, J. J., Egger, M., Whiting, P., & Sterne, J. A. C. (2007). A unification of models for meta-analysis of diagnostic accuracy studies. Biostatistics, 8(2), 239–251. doi:10.1093/biostatistics/kxl004
data("anticcp") fit <- fitReitsmaSubgroup( data = anticcp, TP = TP, FP = FP, FN = FN, TN = TN, study = study, subgroup = generation ) fit summary(fit)data("anticcp") fit <- fitReitsmaSubgroup( data = anticcp, TP = TP, FP = FP, FN = FN, TN = TN, study = study, subgroup = generation ) fit summary(fit)
Fits the Reitsma latent class model with a single categorical covariate, allowing for an imperfect reference standard under conditional independence.
fitReitsmaSubgroupLCA( data, y11, y10, y01, y00, study, subgroup, constrain = NULL, sensspec_constrain = NULL, variances = c("common", "unequal"), prev_variances = c("common", "unequal"), conflevel = 0.95, verbose = FALSE )fitReitsmaSubgroupLCA( data, y11, y10, y01, y00, study, subgroup, constrain = NULL, sensspec_constrain = NULL, variances = c("common", "unequal"), prev_variances = c("common", "unequal"), conflevel = 0.95, verbose = FALSE )
data |
A data.frame containing study-level data. |
y11 |
Number testing positive with both index and reference tests (column name). |
y10 |
Number testing positive with index test but negative with reference test (column name). |
y01 |
Number testing negative with index test but positive with reference test (column name). |
y00 |
Number testing negative with both index and reference tests (column name). |
study |
Study identifier (column name). |
subgroup |
A single categorical study-level subgroup variable (column name). |
constrain |
Optional character string specifying a simplified covariance structure for the index test in the Reitsma LCA model. Allowed values are:
These random-effects simplifications are currently only available for
|
sensspec_constrain |
Optional character vector specifying restrictions on subgroup-specific logit-sensitivity and/or logit-specificity parameters for the index test. This can be useful for testing whether subgroup differences are present in sensitivity, specificity, or both. Allowed values are:
Both constraints may be specified simultaneously, e.g.
If |
variances |
Whether the between-study random-effects variance-covariance
matrix of the index test should be assumed to be |
prev_variances |
Whether the between-study random-effects variance for
logit prevalence should be assumed to be |
conflevel |
Confidence level for confidence intervals. Default is 0.95. |
verbose |
Whether TMB optimization output should be printed (default: FALSE). |
A list of class "ReitsmaSubgroupLCA" with components:
data: the original data set with derived quantities.
fit: Optimization result from nlminb.
sdreport: TMB standard report.
sdreport2: Summary of reported parameters.
vcov: variance-covariance matrix of reported parameters.
sensspec: sensitivity and specificity estimates.
prevref: Estimated (average) prevalence and reference standard sensitivity/specificity with confidence intervals.
LRDOR: Diagnostic odds ratio and likelihood ratios.
RutterGatsonis_recovered: Recovered parameters in the Rutter-Gatsonis (HSROC) parameterization.
subgroups: The subgroup levels used in the model fit.
constrain: Random effects parameters fixed at zero.
sensspec_constrain: Whether sensitivities/specificities are assumed common across subgroups.
variances: Variance structure used in the fitted model.
prev_variances: Prevalence variance structure used in the fitted model.
Liu, Y., Chen, Y., & Chu, H. (2015). A unification of models for meta-analysis of diagnostic accuracy studies without a gold standard. Biometrics, 71(2), 538-547. doi:10.1111/biom.12264
Reitsma, J. B., et al. (2005). Bivariate analysis of sensitivity and specificity produces informative summary measures in diagnostic reviews. Journal of Clinical Epidemiology, 58(10), 982–990. doi:10.1016/j.jclinepi.2005.02.022
Rutter, C. M., & Gatsonis, C. A. (2001). A hierarchical regression approach to meta-analysis of diagnostic test accuracy evaluations. Statistics in Medicine, 20(19), 2865–2884. doi:10.1002/sim.942
Harbord, R. M., Deeks, J. J., Egger, M., Whiting, P., & Sterne, J. A. C. (2007). A unification of models for meta-analysis of diagnostic accuracy studies. Biostatistics, 8(2), 239–251. doi:10.1093/biostatistics/kxl004
data("anticcp") fit <- fitReitsmaSubgroupLCA( data = anticcp, y11 = TP, y10 = FP, y01 = FN, y00 = TN, study = study, subgroup = generation ) fit summary(fit)data("anticcp") fit <- fitReitsmaSubgroupLCA( data = anticcp, y11 = TP, y10 = FP, y01 = FN, y00 = TN, study = study, subgroup = generation ) fit summary(fit)
Fits the Reitsma bivariate random-effects model with a single categorical covariate
for diagnostic test accuracy (DTA) meta-analysis using a binomial-normal
likelihood via a custom TMB template, which
may offer improved numerical robustness in difficult or near-boundary cases.
fitReitsmaSubgroupTMB( data, TP, FP, FN, TN, study, subgroup, constrain = NULL, sensspec_constrain = NULL, variances = c("common", "unequal"), conflevel = 0.95, verbose = FALSE )fitReitsmaSubgroupTMB( data, TP, FP, FN, TN, study, subgroup, constrain = NULL, sensspec_constrain = NULL, variances = c("common", "unequal"), conflevel = 0.95, verbose = FALSE )
data |
A data.frame containing study-level data. |
TP |
True positives (column name). |
FP |
False positives (column name). |
FN |
False negatives (column name). |
TN |
True negatives (column name). |
study |
Study identifier (column name). |
subgroup |
A single categorical study-level subgroup variable (column name). |
constrain |
Optional character string specifying a simplified covariance structure for the Reitsma model. This can be useful for sparse data, small meta-analyses, or for reproducing simplified bivariate models described in the Cochrane Handbook for Diagnostic Test Accuracy Reviews. Allowed values are:
These random-effects simplifications are currently only available for
|
sensspec_constrain |
Optional character vector specifying restrictions on subgroup-specific logit-sensitivity and/or logit-specificity parameters. This can be useful for testing whether subgroup differences are present in sensitivity, specificity, or both. Allowed values are:
Both constraints may be specified simultaneously, e.g.
If |
variances |
Whether the between-study random-effects variance-covariance
matrix should be assumed to be |
conflevel |
Confidence level for confidence intervals. Default is 0.95. |
verbose |
Whether TMB optimization output should be printed (default: FALSE). |
A list of class "ReitsmaSubgroupTMB" with components:
data: the original data set with derived quantities
fit: Optimization result from nlminb.
sdreport: TMB standard report.
sdreport2: Summary of reported parameters.
vcov: variance-covariance matrix of reported parameters.
sensspec: sensitivity and specificity estimates.
LRDOR: Diagnostic odds ratios and likelihood ratios.
RutterGatsonis_recovered: Recovered parameters in the Rutter-Gatsonis (HSROC) parameterization.
subgroups: The subgroup levels used in the model fit.
constrain: Random effects parameters fixed at zero.
sensspec_constrain: Whether sensitivities/specificities are assumed common across subgroups.
variances: Variance structure used in the fitted model.
Reitsma, J. B., et al. (2005). Bivariate analysis of sensitivity and specificity produces informative summary measures in diagnostic reviews. Journal of Clinical Epidemiology, 58(10), 982–990. doi:10.1016/j.jclinepi.2005.02.022
Rutter, C. M., & Gatsonis, C. A. (2001). A hierarchical regression approach to meta-analysis of diagnostic test accuracy evaluations. Statistics in Medicine, 20(19), 2865–2884. doi:10.1002/sim.942
Harbord, R. M., Deeks, J. J., Egger, M., Whiting, P., & Sterne, J. A. C. (2007). A unification of models for meta-analysis of diagnostic accuracy studies. Biostatistics, 8(2), 239–251. doi:10.1093/biostatistics/kxl004
data("anticcp") fit <- fitReitsmaSubgroupTMB( data = anticcp, TP = TP, FP = FP, FN = FN, TN = TN, study = study, subgroup = generation ) fit summary(fit)data("anticcp") fit <- fitReitsmaSubgroupTMB( data = anticcp, TP = TP, FP = FP, FN = FN, TN = TN, study = study, subgroup = generation ) fit summary(fit)
Fits the Reitsma bivariate random-effects model for diagnostic test accuracy (DTA)
meta-analysis using a binomial-normal likelihood via a custom TMB template,
which may offer improved numerical robustness in difficult or near-boundary cases.
fitReitsmaTMB( data, TP, FP, FN, TN, study, constrain = NULL, conflevel = 0.95, verbose = FALSE )fitReitsmaTMB( data, TP, FP, FN, TN, study, constrain = NULL, conflevel = 0.95, verbose = FALSE )
data |
A data.frame containing study-level data. |
TP |
True positives (column name). |
FP |
False positives (column name). |
FN |
False negatives (column name). |
TN |
True negatives (column name). |
study |
Study identifier (column name). |
constrain |
Optional character string specifying a simplified covariance structure for the Reitsma model. This can be useful for sparse data, small meta-analyses, or for reproducing simplified bivariate models described in the Cochrane Handbook for Diagnostic Test Accuracy Reviews. Allowed values are:
|
conflevel |
Confidence level for confidence intervals. Default is 0.95. |
verbose |
Whether TMB optimization output should be printed (default: FALSE). |
A list of class "ReitsmaTMB" with components:
data: the original data set with derived quantities
fit: Optimization result from nlminb.
sdreport: TMB standard report.
sdreport2: Summary of reported parameters.
vcov: variance-covariance matrix of reported parameters.
sensspec: sensitivity and specificity estimates.
LRDOR: Diagnostic odds ratio and likelihood ratios.
RutterGatsonis_recovered: Recovered parameters in the Rutter-Gatsonis (HSROC) parameterization.
constrain: Random effects parameters fixed at zero.
Reitsma, J. B., et al. (2005). Bivariate analysis of sensitivity and specificity produces informative summary measures in diagnostic reviews. Journal of Clinical Epidemiology, 58(10), 982–990. doi:10.1016/j.jclinepi.2005.02.022
Rutter, C. M., & Gatsonis, C. A. (2001). A hierarchical regression approach to meta-analysis of diagnostic test accuracy evaluations. Statistics in Medicine, 20(19), 2865–2884. doi:10.1002/sim.942
Harbord, R. M., Deeks, J. J., Egger, M., Whiting, P., & Sterne, J. A. C. (2007). A unification of models for meta-analysis of diagnostic accuracy studies. Biostatistics, 8(2), 239–251. doi:10.1093/biostatistics/kxl004
data("anticcp") fit <- fitReitsmaTMB( data = anticcp, TP = TP, FP = FP, FN = FN, TN = TN, study = study ) summary(fit)data("anticcp") fit <- fitReitsmaTMB( data = anticcp, TP = TP, FP = FP, FN = FN, TN = TN, study = study ) summary(fit)
Fits the hierarchical summary receiver operating characteristic (HSROC) model as proposed by Rutter and Gatsonis for meta-analysis of diagnostic test accuracy (DTA) studies using Template Model Builder (TMB).
fitRutterGatsonis( data, TP, FP, FN, TN, study, conflevel = 0.95, constrain = NULL, spec = NULL, verbose = FALSE )fitRutterGatsonis( data, TP, FP, FN, TN, study, conflevel = 0.95, constrain = NULL, spec = NULL, verbose = FALSE )
data |
A data.frame containing study-level data. |
TP |
True positives (column name). |
FP |
False positives (column name). |
FN |
False negatives (column name). |
TN |
True negatives (column name). |
study |
Study identifier (column name). |
conflevel |
Confidence level for confidence intervals. Default is 0.95. |
constrain |
Optional character vector specifying model parameters that should be fixed at zero during estimation. This can be useful for sparse data, small meta-analyses, or for reproducing simplified HSROC models described in the Cochrane Handbook for Diagnostic Test Accuracy Reviews. Allowed values are:
Multiple constraints may be specified simultaneously, e.g.
If |
spec |
Optional specificity value at which sensitivity is estimated.
If |
verbose |
Whether TMB optimization output should be printed (default: FALSE). |
The function internally transforms the data into long format and fits the model via maximum likelihood using TMB. Random effects are included for study-specific accuracy and threshold parameters.
Reitsma parameterization is recovered from the fitted HSROC parameters.
The constrain argument allows simplified HSROC models to be
fitted by fixing selected parameters at zero. These constrained models
may improve numerical stability in sparse datasets and can be used to
reproduce several simplified models presented in the Cochrane Handbook
for Diagnostic Test Accuracy Reviews.
Constraints are imposed using parameter mapping within Template Model Builder (TMB), so constrained parameters are excluded from numerical optimization and treated as fixed constants.
An object of class "RutterGatsonis" containing:
Processed input data with derived quantities.
Optimization result from nlminb.
TMB standard report.
Summary of reported parameters.
Estimated sensitivity at given specificity with confidence intervals.
Recovered parameters in the Reitsma parameterization.
Parameters fixed at zero.
Requires a compiled TMB model named "RutterGatsonis".
Reitsma, J. B., et al. (2005). Bivariate analysis of sensitivity and specificity produces informative summary measures in diagnostic reviews. Journal of Clinical Epidemiology, 58(10), 982–990. doi:10.1016/j.jclinepi.2005.02.022
Rutter, C. M., & Gatsonis, C. A. (2001). A hierarchical regression approach to meta-analysis of diagnostic test accuracy evaluations. Statistics in Medicine, 20(19), 2865–2884. doi:10.1002/sim.942
Harbord, R. M., Deeks, J. J., Egger, M., Whiting, P., & Sterne, J. A. C. (2007). A unification of models for meta-analysis of diagnostic accuracy studies. Biostatistics, 8(2), 239–251. doi:10.1093/biostatistics/kxl004
data("RF") fit <- fitRutterGatsonis( data = RF, TP = TP, FP = FP, FN = FN, TN = TN, study = study ) summary(fit)data("RF") fit <- fitRutterGatsonis( data = RF, TP = TP, FP = FP, FN = FN, TN = TN, study = study ) summary(fit)
Fits the Rutter and Gatsonis latent class model for diagnostic test accuracy (DTA), allowing for an imperfect reference standard under conditional independence.
fitRutterGatsonisLCA( data, y11, y10, y01, y00, study, conflevel = 0.95, constrain = NULL, spec = NULL, verbose = FALSE )fitRutterGatsonisLCA( data, y11, y10, y01, y00, study, conflevel = 0.95, constrain = NULL, spec = NULL, verbose = FALSE )
data |
A data.frame containing study-level data. |
y11 |
Number testing positive with both index and reference tests (column name). |
y10 |
Number testing positive with index test but negative with reference test (column name). |
y01 |
Number testing negative with index test but positive with reference test (column name). |
y00 |
Number testing negative with both index and reference tests (column name). |
study |
Study identifier (column name). |
conflevel |
Confidence level for confidence intervals. Default is 0.95. |
constrain |
Optional character vector specifying model parameters of the index test that should be fixed at zero during estimation. Allowed values are:
Multiple constraints may be specified simultaneously, e.g.
If |
spec |
Optional specificity value at which sensitivity is estimated.
If |
verbose |
Whether TMB optimization output should be printed (default: FALSE). |
An object of class "RutterGatsonisLCA" containing:
Processed input data with derived quantities.
Optimization result from nlminb.
TMB standard report.
Summary of reported parameters.
Estimated index test sensitivity at given specificity with confidence intervals.
Estimated (average) prevalence and reference standard sensitivity/specificity with confidence intervals.
Recovered parameters in the Reitsma parameterization.
Parameters fixed at zero.
Liu, Y., Chen, Y., & Chu, H. (2015). A unification of models for meta-analysis of diagnostic accuracy studies without a gold standard. Biometrics, 71(2), 538-547. doi:10.1111/biom.12264
Reitsma, J. B., et al. (2005). Bivariate analysis of sensitivity and specificity produces informative summary measures in diagnostic reviews. Journal of Clinical Epidemiology, 58(10), 982–990. doi:10.1016/j.jclinepi.2005.02.022
Rutter, C. M., & Gatsonis, C. A. (2001). A hierarchical regression approach to meta-analysis of diagnostic test accuracy evaluations. Statistics in Medicine, 20(19), 2865–2884. doi:10.1002/sim.942
Harbord, R. M., Deeks, J. J., Egger, M., Whiting, P., & Sterne, J. A. C. (2007). A unification of models for meta-analysis of diagnostic accuracy studies. Biostatistics, 8(2), 239–251. doi:10.1093/biostatistics/kxl004
data("anticcp") fit <- fitRutterGatsonisLCA( data = anticcp, y11 = TP, y10 = FP, y01 = FN, y00 = TN, study = study ) fit summary(fit)data("anticcp") fit <- fitRutterGatsonisLCA( data = anticcp, y11 = TP, y10 = FP, y01 = FN, y00 = TN, study = study ) fit summary(fit)
Fits a general HSROC meta-regression model using user-supplied design matrices for estimation and prediction.
fitRutterGatsonisReg( data, TP, FP, FN, TN, study, Z, Z_pred = NULL, map = NULL, init = NULL, spec = NULL, conflevel = 0.95, verbose = FALSE )fitRutterGatsonisReg( data, TP, FP, FN, TN, study, Z, Z_pred = NULL, map = NULL, init = NULL, spec = NULL, conflevel = 0.95, verbose = FALSE )
data |
A data.frame containing study-level data. |
TP |
True positives (column name). |
FP |
False positives (column name). |
FN |
False negatives (column name). |
TN |
True negatives (column name). |
study |
Study identifier (column name). |
Z |
Design matrix containing covariate values for model fitting.
The current implementation is intended primarily for study-level
covariates. In the long-format representation, this typically means
that each study is represented by two consecutive rows with identical
covariate values. The number of rows of |
Z_pred |
Prediction design matrix used to obtain covariate-specific
parameter estimates and SROC curves. Each row defines a covariate pattern
at which predictions are evaluated. The number of columns of
|
map |
Optional named list of parameter mappings passed to
Parameter mapping allows selected model parameters to be fixed or constrained during estimation. This can be useful for fitting simplified HSROC models, imposing equality constraints, or reproducing model specifications described in the literature. Each component of This is an advanced feature intended primarily for users familiar with Template Model Builder (TMB). If Example |
init |
Optional list of initial parameter values.
If
The lengths of |
spec |
Optional specificity value or vector of specificity values
at which sensitivity is evaluated for each covariate pattern specified
in |
conflevel |
Confidence level for confidence intervals.
Default is |
verbose |
Logical indicating whether TMB optimization output should
be printed (default: |
This function is intended for advanced users who wish to specify design
matrices directly. The user is responsible for constructing appropriate
design matrices, choosing prediction covariate patterns through
Z_pred, and interpreting or visualizing the resulting regression
model.
By default, all fixed and random effects are initialized at zero.
For difficult optimization problems, user-supplied starting values may be
provided through the init argument.
The fitted model estimates covariate effects on the HSROC accuracy,
threshold, and optionally shape parameters. Predicted sensitivities are
obtained by evaluating the resulting SROC curve(s) at the specificity
value(s) supplied through spec and the covariate patterns defined
by Z_pred.
An object of class "RutterGatsonisReg" containing:
Processed input data with derived quantities.
Optimization result returned by nlminb.
TMB standard report object.
Summary of reported model parameters and derived quantities.
Estimated sensitivities at the specified specificity value(s), including confidence intervals.
Requires a compiled TMB model named "RutterGatsonisReg".
Reitsma, J. B., Glas, A. S., Rutjes, A. W. S., Scholten, R. J. P. M., Bossuyt, P. M., & Zwinderman, A. H. (2005). Bivariate analysis of sensitivity and specificity produces informative summary measures in diagnostic reviews. Journal of Clinical Epidemiology, 58(10), 982–990. doi:10.1016/j.jclinepi.2005.02.022
Rutter, C. M., & Gatsonis, C. A. (2001). A hierarchical regression approach to meta-analysis of diagnostic test accuracy evaluations. Statistics in Medicine, 20(19), 2865–2884. doi:10.1002/sim.942
Harbord, R. M., Deeks, J. J., Egger, M., Whiting, P., & Sterne, J. A. C. (2007). A unification of models for meta-analysis of diagnostic accuracy studies. Biostatistics, 8(2), 239–251. doi:10.1093/biostatistics/kxl004
data("RF") RF2 <- RF[RF$method %in% c("LA","ELISA","Nephelometry"),] RF2$method <- factor(RF2$method,levels=c("LA","ELISA","Nephelometry")) Z <- model.matrix(~ method, data = RF2) Z <- Z[rep(seq_len(nrow(Z)), each = 2), , drop = FALSE] Z_pred <- matrix(c(1,0,0,1,1,0,1,0,1),ncol=3,nrow=3,byrow=TRUE) fit <- fitRutterGatsonisReg( data = RF2, TP = TP, FP = FP, FN = FN, TN = TN, study = study, Z = Z, Z_pred = Z_pred ) summary(fit)data("RF") RF2 <- RF[RF$method %in% c("LA","ELISA","Nephelometry"),] RF2$method <- factor(RF2$method,levels=c("LA","ELISA","Nephelometry")) Z <- model.matrix(~ method, data = RF2) Z <- Z[rep(seq_len(nrow(Z)), each = 2), , drop = FALSE] Z_pred <- matrix(c(1,0,0,1,1,0,1,0,1),ncol=3,nrow=3,byrow=TRUE) fit <- fitRutterGatsonisReg( data = RF2, TP = TP, FP = FP, FN = FN, TN = TN, study = study, Z = Z, Z_pred = Z_pred ) summary(fit)
The function fits an HSROC model with a single categorical study-level covariate (subgroup).
fitRutterGatsonisSubgroup( data, TP, FP, FN, TN, study, subgroup, constrain = NULL, spec = NULL, conflevel = 0.95, verbose = FALSE )fitRutterGatsonisSubgroup( data, TP, FP, FN, TN, study, subgroup, constrain = NULL, spec = NULL, conflevel = 0.95, verbose = FALSE )
data |
A data.frame containing study-level data. |
TP |
True positives (column name). |
FP |
False positives (column name). |
FN |
False negatives (column name). |
TN |
True negatives (column name). |
study |
Study identifier (column name). |
subgroup |
A single categorical study-level subgroup variable (column name). |
constrain |
Optional character vector specifying model parameters that should be constrained during estimation. This can be useful for sparse data, small meta-analyses, or for reproducing simplified HSROC models described in the Cochrane Handbook for Diagnostic Test Accuracy Reviews. Allowed values are:
Multiple constraints may be specified simultaneously, e.g.
If |
spec |
Optional specificity value or vector of specificity values at which
sensitivity is estimated. If |
conflevel |
Confidence level for confidence intervals. Default is 0.95. |
verbose |
Whether TMB optimization output should be printed (default: FALSE). |
The function fits an HSROC model with a single categorical study-level covariate (subgroup). Separate subgroup effects are estimated for the accuracy and threshold parameters. Optionally, subgroup-specific effects can also be estimated for the shape parameter.
The fitted model returns subgroup-specific summary sensitivity estimates
evaluated at user-specified specificity values. If spec = NULL, the
median observed specificity is used as a proxy.
This function is intended as a convenient wrapper for subgroup analyses
with a single categorical covariate and provides output suitable for
dedicated summary(), plot(), and forest() methods.
An object of class "RutterGatsonisSubgroup" containing:
Processed input data with derived quantities.
Optimization result from nlminb.
TMB standard report.
Summary of reported subgroup-specific parameters.
Estimated subgroup-specific sensitivities at the given specificity value(s), with confidence intervals.
Constraints on parameters applied during model fitting.
The subgroup levels used in the model fit.
Requires a compiled TMB model named "RutterGatsonisReg".
Reitsma, J. B., et al. (2005). Bivariate analysis of sensitivity and specificity produces informative summary measures in diagnostic reviews. Journal of Clinical Epidemiology, 58(10), 982–990. doi:10.1016/j.jclinepi.2005.02.022
Rutter, C. M., & Gatsonis, C. A. (2001). A hierarchical regression approach to meta-analysis of diagnostic test accuracy evaluations. Statistics in Medicine, 20(19), 2865–2884. doi:10.1002/sim.942
Harbord, R. M., Deeks, J. J., Egger, M., Whiting, P., & Sterne, J. A. C. (2007). A unification of models for meta-analysis of diagnostic accuracy studies. Biostatistics, 8(2), 239–251. doi:10.1093/biostatistics/kxl004
data("RF") fit <- fitRutterGatsonisSubgroup( data = RF, TP = TP, FP = FP, FN = FN, TN = TN, study = study, subgroup = method ) summary(fit)data("RF") fit <- fitRutterGatsonisSubgroup( data = RF, TP = TP, FP = FP, FN = FN, TN = TN, study = study, subgroup = method ) summary(fit)
The function fits an HSROC model with a single categorical study-level covariate (subgroup), allowing for an imperfect reference standard assuming conditional independence.
fitRutterGatsonisSubgroupLCA( data, y11, y10, y01, y00, study, subgroup, constrain = NULL, prev_variances = c("common", "unequal"), spec = NULL, conflevel = 0.95, verbose = FALSE )fitRutterGatsonisSubgroupLCA( data, y11, y10, y01, y00, study, subgroup, constrain = NULL, prev_variances = c("common", "unequal"), spec = NULL, conflevel = 0.95, verbose = FALSE )
data |
A data.frame containing study-level data. |
y11 |
Number testing positive with both index and reference tests (column name). |
y10 |
Number testing positive with index test but negative with reference test (column name). |
y01 |
Number testing negative with index test but positive with reference test (column name). |
y00 |
Number testing negative with both index and reference tests (column name). |
study |
Study identifier (column name). |
subgroup |
A single categorical study-level subgroup variable (column name). |
constrain |
Optional character vector specifying model parameters that should be constrained during estimation. Allowed values are:
Multiple constraints may be specified simultaneously, e.g.
If |
prev_variances |
Whether the between-study random-effects variance for
logit prevalence should be assumed to be |
spec |
Optional specificity value at which sensitivity is estimated.
If |
conflevel |
Confidence level for confidence intervals. Default is 0.95. |
verbose |
Whether TMB optimization output should be printed (default: FALSE). |
An object of class "RutterGatsonisSubgroupLCA" containing:
Processed input data with derived quantities.
Optimization result from nlminb.
TMB standard report.
Summary of reported subgroup-specific parameters.
Estimated subgroup-specific index test sensitivities at the given specificity value(s), with confidence intervals.
Estimated (average) prevalence and reference standard sensitivity/specificity with confidence intervals.
Constraints on parameters applied during model fitting.
The subgroup levels used in the model fit.
Prevalence variance structure used in the fitted model.
Requires a compiled TMB model named "RutterGatsonisSubgroupLCA".
Liu, Y., Chen, Y., & Chu, H. (2015). A unification of models for meta-analysis of diagnostic accuracy studies without a gold standard. Biometrics, 71(2), 538-547. doi:10.1111/biom.12264
Reitsma, J. B., et al. (2005). Bivariate analysis of sensitivity and specificity produces informative summary measures in diagnostic reviews. Journal of Clinical Epidemiology, 58(10), 982–990. doi:10.1016/j.jclinepi.2005.02.022
Rutter, C. M., & Gatsonis, C. A. (2001). A hierarchical regression approach to meta-analysis of diagnostic test accuracy evaluations. Statistics in Medicine, 20(19), 2865–2884. doi:10.1002/sim.942
Harbord, R. M., Deeks, J. J., Egger, M., Whiting, P., & Sterne, J. A. C. (2007). A unification of models for meta-analysis of diagnostic accuracy studies. Biostatistics, 8(2), 239–251. doi:10.1093/biostatistics/kxl004
data("schuetz") fit <- fitRutterGatsonisSubgroupLCA( data = schuetz, y11 = TP, y10 = FP, y01 = FN, y00 = TN, study = study, subgroup = test ) fit summary(fit)data("schuetz") fit <- fitRutterGatsonisSubgroupLCA( data = schuetz, y11 = TP, y10 = FP, y01 = FN, y00 = TN, study = study, subgroup = test ) fit summary(fit)
Produces coupled forest plots.
forest(x, ...)forest(x, ...)
x |
Object |
... |
Additional arguments |
Invisibly returns a forestploter object. Users may further modify the plot
using forestploter functions before printing or exporting.
Provides coupled forest plots of sensitivities and specificities with Clopper-Pearson confidence limits.
## S3 method for class 'HoyerAFT' forest(x, conflevel = 0.95, ...)## S3 method for class 'HoyerAFT' forest(x, conflevel = 0.95, ...)
x |
Object of class |
conflevel |
Confidence level for confidence intervals. Default is 0.95. |
... |
Additional graphical arguments (not currently in use) |
Invisibly returns a forestploter object. Users may further modify the plot
using forestploter functions before printing or exporting.
Provides coupled forest plots of sensitivities and specificities with Clopper-Pearson confidence limits.
## S3 method for class 'Reitsma' forest(x, conflevel = 0.95, ...)## S3 method for class 'Reitsma' forest(x, conflevel = 0.95, ...)
x |
Object of class |
conflevel |
Confidence level for confidence intervals. Default is 0.95. |
... |
Additional graphical arguments (not currently in use) |
Invisibly returns a forestploter object. Users may further modify the plot
using forestploter functions before printing or exporting.
Study-specific sensitivities and specificities are empirical Bayes estimates derived from the fitted latent class model. Confidence intervals are based on the conditional posterior variance of the study-specific random effects obtained from the TMB Laplace approximation.
## S3 method for class 'ReitsmaLCA' forest(x, conflevel = 0.95, ...)## S3 method for class 'ReitsmaLCA' forest(x, conflevel = 0.95, ...)
x |
Object of class |
conflevel |
Confidence level for confidence intervals. Default is 0.95. |
... |
Additional graphical arguments (not currently in use) |
Invisibly returns a forestploter object. Users may further modify the plot
using forestploter functions before printing or exporting.
Provides coupled forest plots of sensitivities and specificities with Clopper-Pearson confidence limits.
## S3 method for class 'ReitsmaSubgroup' forest( x, conflevel = 0.95, subgroup_label = "Subgroup", order = c("study", "subgroup"), ... )## S3 method for class 'ReitsmaSubgroup' forest( x, conflevel = 0.95, subgroup_label = "Subgroup", order = c("study", "subgroup"), ... )
x |
Object of class |
conflevel |
Confidence level for confidence intervals. Default is 0.95. |
subgroup_label |
Column name for the subgroup. Defaults to |
order |
Specifies the ordering of studies
in the forest plot. Can be |
... |
Additional graphical arguments (not currently in use) |
Invisibly returns a forestploter object. Users may further modify the plot
using forestploter functions before printing or exporting.
Study-specific sensitivities and specificities are empirical Bayes estimates derived from the fitted latent class model. Confidence intervals are based on the conditional posterior variance of the study-specific random effects obtained from the TMB Laplace approximation.
## S3 method for class 'ReitsmaSubgroupLCA' forest( x, conflevel = 0.95, subgroup_label = "Subgroup", order = c("study", "subgroup"), ... )## S3 method for class 'ReitsmaSubgroupLCA' forest( x, conflevel = 0.95, subgroup_label = "Subgroup", order = c("study", "subgroup"), ... )
x |
Object of class |
conflevel |
Confidence level for confidence intervals. Default is 0.95. |
subgroup_label |
Column name for the subgroup. Defaults to |
order |
Specifies the ordering of studies
in the forest plot. Can be |
... |
Additional graphical arguments (not currently in use) |
Invisibly returns a forestploter object. Users may further modify the plot
using forestploter functions before printing or exporting.
Provides coupled forest plots of sensitivities and specificities with Clopper-Pearson confidence limits.
## S3 method for class 'ReitsmaSubgroupTMB' forest( x, conflevel = 0.95, subgroup_label = "Subgroup", order = c("study", "subgroup"), ... )## S3 method for class 'ReitsmaSubgroupTMB' forest( x, conflevel = 0.95, subgroup_label = "Subgroup", order = c("study", "subgroup"), ... )
x |
Object of class |
conflevel |
Confidence level for confidence intervals. Default is 0.95. |
subgroup_label |
Column name for the subgroup. Defaults to |
order |
Specifies the ordering of studies
in the forest plot. Can be |
... |
Additional graphical arguments (not currently in use) |
Invisibly returns a forestploter object. Users may further modify the plot
using forestploter functions before printing or exporting.
Provides coupled forest plots of sensitivities and specificities with Clopper-Pearson confidence limits.
## S3 method for class 'RutterGatsonis' forest(x, conflevel = 0.95, ...)## S3 method for class 'RutterGatsonis' forest(x, conflevel = 0.95, ...)
x |
Object of class |
conflevel |
Confidence level for confidence intervals. Default is 0.95. |
... |
Additional graphical arguments (not currently in use) |
Invisibly returns a forestploter object. Users may further modify the plot
using forestploter functions before printing or exporting.
Study-specific sensitivities and specificities are empirical Bayes estimates derived from the fitted latent class model. Confidence intervals are based on the conditional posterior variance of the study-specific random effects obtained from the TMB Laplace approximation.
## S3 method for class 'RutterGatsonisLCA' forest(x, conflevel = 0.95, ...)## S3 method for class 'RutterGatsonisLCA' forest(x, conflevel = 0.95, ...)
x |
Object of class |
conflevel |
Confidence level for confidence intervals. Default is 0.95. |
... |
Additional graphical arguments (not currently in use) |
Invisibly returns a forestploter object. Users may further modify the plot
using forestploter functions before printing or exporting.
Provides coupled forest plots of sensitivities and specificities with Clopper-Pearson confidence limits.
## S3 method for class 'RutterGatsonisSubgroup' forest( x, conflevel = 0.95, subgroup_label = "Subgroup", order = c("study", "subgroup"), ... )## S3 method for class 'RutterGatsonisSubgroup' forest( x, conflevel = 0.95, subgroup_label = "Subgroup", order = c("study", "subgroup"), ... )
x |
Object of class |
conflevel |
Confidence level for confidence intervals. Default is 0.95. |
subgroup_label |
Column name for the subgroup. Defaults to |
order |
Specifies the ordering of studies
in the forest plot. Can be |
... |
Additional graphical arguments (not currently in use) |
Invisibly returns a forestploter object. Users may further modify the plot
using forestploter functions before printing or exporting.
Study-specific sensitivities and specificities are empirical Bayes estimates derived from the fitted latent class model. Confidence intervals are based on the conditional posterior variance of the study-specific random effects obtained from the TMB Laplace approximation.
## S3 method for class 'RutterGatsonisSubgroupLCA' forest( x, conflevel = 0.95, subgroup_label = "Subgroup", order = c("study", "subgroup"), ... )## S3 method for class 'RutterGatsonisSubgroupLCA' forest( x, conflevel = 0.95, subgroup_label = "Subgroup", order = c("study", "subgroup"), ... )
x |
Object of class |
conflevel |
Confidence level for confidence intervals. Default is 0.95. |
subgroup_label |
Column name for the subgroup. Defaults to |
order |
Specifies the ordering of studies
in the forest plot. Can be |
... |
Additional graphical arguments (not currently in use) |
Invisibly returns a forestploter object. Users may further modify the plot
using forestploter functions before printing or exporting.
Computes initial values for the threshold-based bivariate time-to-event model of Hoyer et al. (2018).
initHoyerAFT(restructured, dist = "loglogistic")initHoyerAFT(restructured, dist = "loglogistic")
restructured |
A data frame in interval format as produced by
|
dist |
Character string specifying the parametric distribution
used in the survival regression models. Must be one of:
|
The function fits separate intercept-only parametric survival models for diseased and non-diseased groups using weighted interval-censored likelihoods. It further derives initial estimates of between-study variability based on study-specific weighted averages of log-thresholds.
To ensure compatibility with survival::survreg, interval bounds
are modified as follows:
Left-censored intervals (ctype = 1) are assigned a small
positive lower bound.
Right-censored intervals (ctype = 3) are assigned an
infinite upper bound.
A single-row data frame containing initial parameter values:
Intercept for non-diseased group
Scale parameter for non-diseased group
Intercept for diseased group
Scale parameter for diseased group
Standard deviation of random effects (non-diseased)
Standard deviation of random effects (diseased)
Correlation between random effects
Numeric code for the distribution (1 = Weibull, 2 = lognormal, 3 = loglogistic)
Hoyer, A., Hirt, S., Kuss, O. (2018). Meta-analysis of full ROC curves using bivariate time-to-event models for interval-censored data. Research Synthesis Methods, 9(1), 62-72. doi:10.1002/jrsm.1273
data("diabetes") res <- restructure_data( data = diabetes, TP = TP, FP = FP, FN = FN, TN = TN, threshold = threshold, study = study, smallest = 2, largest = 10 ) init <- initHoyerAFT(res$restructured)data("diabetes") res <- restructure_data( data = diabetes, TP = TP, FP = FP, FN = FN, TN = TN, threshold = threshold, study = study, smallest = 2, largest = 10 ) init <- initHoyerAFT(res$restructured)
Returns the maximized log-likelihood for a fitted diagnostic test
accuracy meta-analysis model. The returned value is an object of class
"logLik" and includes the number of estimated parameters (df) and
the number of observations used in model fitting (nobs).
## S3 method for class 'DTAmodel' logLik(object, ...) ## S3 method for class 'HoyerAFT' logLik(object, ...) ## S3 method for class 'Reitsma' logLik(object, ...) ## S3 method for class 'ReitsmaSubgroup' logLik(object, ...) ## S3 method for class 'ReitsmaLCA' logLik(object, ...) ## S3 method for class 'ReitsmaSubgroupLCA' logLik(object, ...) ## S3 method for class 'ReitsmaSubgroupTMB' logLik(object, ...) ## S3 method for class 'ReitsmaTMB' logLik(object, ...)## S3 method for class 'DTAmodel' logLik(object, ...) ## S3 method for class 'HoyerAFT' logLik(object, ...) ## S3 method for class 'Reitsma' logLik(object, ...) ## S3 method for class 'ReitsmaSubgroup' logLik(object, ...) ## S3 method for class 'ReitsmaLCA' logLik(object, ...) ## S3 method for class 'ReitsmaSubgroupLCA' logLik(object, ...) ## S3 method for class 'ReitsmaSubgroupTMB' logLik(object, ...) ## S3 method for class 'ReitsmaTMB' logLik(object, ...)
object |
A fitted model object. |
... |
Not used. |
An object of class "logLik".
This is the pap dataset from Fahey et al. (1995) from a meta-analysis comparing Papanicolaou (Pap) test results with histology for the diagnosis of cervical cancer.
pappap
A data frame with 59 rows and 6 variables:
Study identifier
Test taken during screening (SC) or follow-up (FU)
Number testing positive with both tests
Number testing positive with index test but negative with reference test
Number testing negative with index test but positive with reference test
Number testing negative with both tests
The data set was reconstructed from the SAS code in the supplementary material from Liu et al. (2015).
Liu, Y., Chen, Y., & Chu, H. (2015). A unification of models for meta-analysis of diagnostic accuracy studies without a gold standard. Biometrics, 71(2), 538-547. doi:10.1111/biom.12264
Fahey, M., Irwig, L., & Macaskill, P. (1995). Meta-analysis of pap test accuracy. American Journal of Epidemiology, 141(7), 680-689. doi:10.1093/oxfordjournals.aje.a117485
Produces a hierarchical summary receiver operating characteristic (HSROC) plot from a fitted HoyerAFT model. The plot shows study-level sensitivity and specificity estimates together with the meta-analytic HSROC curve derived from the fitted model.
## S3 method for class 'HoyerAFT' plot( x, symbol = c("rectangle", "ellipse", "diamond", "triangle", "cross", "plus", "star"), scale = 0.02, size = c("equal", "sampsize", "se", "sampsize_revman", "se_revman"), HSROC = TRUE, thresholdrange = NULL, main = "Diagnostic Test Accuracy Meta-Analysis", studyCI = FALSE, conflevel = 0.95, studylabels = FALSE, legend = TRUE, ... )## S3 method for class 'HoyerAFT' plot( x, symbol = c("rectangle", "ellipse", "diamond", "triangle", "cross", "plus", "star"), scale = 0.02, size = c("equal", "sampsize", "se", "sampsize_revman", "se_revman"), HSROC = TRUE, thresholdrange = NULL, main = "Diagnostic Test Accuracy Meta-Analysis", studyCI = FALSE, conflevel = 0.95, studylabels = FALSE, legend = TRUE, ... )
x |
An object of class
|
symbol |
Character string specifying the symbol used for study-level
estimates. One of |
scale |
Numeric scaling factor controlling study-symbol dimensions.
The default is |
size |
Character string controlling display of study-level point estimates:
|
HSROC |
if |
thresholdrange |
A numeric vector of length 2 giving the range of
threshold over which sensitivities and specificities are predicted.
If |
main |
Character string giving the main title of the plot.
Defaults to |
studyCI |
Whether study-level confidence
intervals should be displayed for the observed sensitivity and
specificity estimates. Defaults to |
conflevel |
Confidence level for the study-level confidence
intervals. Default is |
studylabels |
Whether study identifiers should
be displayed next to the study-level estimates. Defaults to
|
legend |
Whether a legend should be displayed. Default is |
... |
Additional graphical arguments (currently unused). |
The plot includes:
Study-specific sensitivity and false positive rate estimates
Symbols representing study observations, with dimensions determined by the selected graphical sizing method.
Lines connecting thresholds within studies
A meta-analytic HSROC curve based on the fitted AFT model
The HSROC curve is constructed using the estimated model parameters and depends on the specified distribution:
Weibull
Lognormal
Loglogistic
The plot is constructed on the ROC scale with sensitivity on the y-axis and specificity on the x-axis (displayed as 1 - false positive rate on a reversed axis).
No return value. Called for its side effect of producing a plot.
Produces a summary ROC plot for objects of class "Reitsma"
obtained from fitReitsma. The plot displays study-level
estimates of sensitivity and specificity, the summary operating point,
and corresponding confidence and prediction regions. Optionally, the
HSROC (hierarchical summary ROC) curve can be overlaid.
## S3 method for class 'Reitsma' plot( x, symbol = c("rectangle", "ellipse", "diamond", "triangle", "cross", "plus", "star"), scale = 0.02, size = c("fisher", "fisher_revman", "equal", "sampsize", "se", "sampsize_revman", "se_revman"), main = "Diagnostic Test Accuracy Meta-Analysis", HSROC = FALSE, specrange = c(0.7, 0.995), conflevel = 0.95, predlevel = 0.95, studyCI = FALSE, studylabels = FALSE, legend = TRUE, ... )## S3 method for class 'Reitsma' plot( x, symbol = c("rectangle", "ellipse", "diamond", "triangle", "cross", "plus", "star"), scale = 0.02, size = c("fisher", "fisher_revman", "equal", "sampsize", "se", "sampsize_revman", "se_revman"), main = "Diagnostic Test Accuracy Meta-Analysis", HSROC = FALSE, specrange = c(0.7, 0.995), conflevel = 0.95, predlevel = 0.95, studyCI = FALSE, studylabels = FALSE, legend = TRUE, ... )
x |
An object of class |
symbol |
Character string specifying the symbol used for study-level
estimates. One of |
scale |
Numeric scaling factor controlling study-symbol dimensions.
The default is |
size |
Character string controlling display of study-level point estimates:
|
main |
Character string giving the main title of the plot.
Defaults to |
HSROC |
if |
specrange |
A numeric vector of length 2 giving the range of
specificities over which the HSROC curve is plotted.
Defaults to |
conflevel |
Confidence level for the confidence region. Default is |
predlevel |
Confidence level for the prediction region. Default is |
studyCI |
Whether study-level confidence
intervals should be displayed for the observed sensitivity and
specificity estimates. Defaults to |
studylabels |
Whether study identifiers should
be displayed next to the study-level estimates. Defaults to
|
legend |
Whether a legend should be displayed. Default is |
... |
Additional graphical arguments passed to plotting functions. |
The plot is constructed on the ROC scale with sensitivity on the y-axis and specificity on the x-axis (displayed as 1 - false positive rate on a reversed axis).
Study-specific estimates are shown using the selected symbol (rectangles by default), where the size reflects approximate study weights derived from the Fisher information matrix (default).
The following elements are displayed:
Study-level sensitivity and specificity estimates
Summary (pooled) estimate
confidence region around the summary point
prediction region reflecting between-study variability
Optional HSROC curve (if HSROC = TRUE)
Confidence and prediction regions are derived using the delta method based on the estimated variance-covariance structure of the model.
No return value. Called for its side effect of producing a plot.
Freeman, S. C., Kerby, C. R., Patel, A., Cooper, N. J., Quinn, T., & Sutton, A. J. (2019). Development of an interactive web-based tool to conduct and interrogate meta-analysis of diagnostic test accuracy studies: MetaDTA. BMC Medical Research Methodology, 19, 81. doi:10.1186/s12874-019-0724-x
Harbord, R. M., Deeks, J. J., Egger, M., Whiting, P., & Sterne, J. A. C. (2007). A unification of models for meta-analysis of diagnostic accuracy studies. Biostatistics, 8(2), 239–251. doi:10.1093/biostatistics/kxl004
Riley, R. D., Ensor, J., Jackson, D., & Burke, D. L. (2018). Deriving percentage study weights in multi-parameter meta-analysis models: with application to meta-regression, network meta-analysis and one-stage individual participant data models. Statistical Methods in Medical Research, 27(10), 2885–2905. doi:10.1177/0962280216688033
Produces a summary ROC plot for objects of class "ReitsmaLCA"
obtained from fitReitsmaLCA. Study-specific sensitivities and
specificities are empirical Bayes estimates derived from the fitted latent
class model.
## S3 method for class 'ReitsmaLCA' plot( x, symbol = c("rectangle", "ellipse", "diamond", "triangle", "cross", "plus", "star"), scale = 0.02, size = c("eb", "equal", "sampsize", "eb_revman", "sampsize_revman"), main = "Diagnostic Test Accuracy Meta-Analysis", HSROC = FALSE, specrange = c(0.7, 0.995), conflevel = 0.95, predlevel = 0.95, studyCI = FALSE, studylabels = FALSE, legend = TRUE, ... )## S3 method for class 'ReitsmaLCA' plot( x, symbol = c("rectangle", "ellipse", "diamond", "triangle", "cross", "plus", "star"), scale = 0.02, size = c("eb", "equal", "sampsize", "eb_revman", "sampsize_revman"), main = "Diagnostic Test Accuracy Meta-Analysis", HSROC = FALSE, specrange = c(0.7, 0.995), conflevel = 0.95, predlevel = 0.95, studyCI = FALSE, studylabels = FALSE, legend = TRUE, ... )
x |
An object of class |
symbol |
Character string specifying the symbol used for study-level
estimates. One of |
scale |
Numeric scaling factor controlling study-symbol dimensions.
The default is |
size |
Character string controlling display of study-level point estimates:
|
main |
Character string giving the main title of the plot.
Defaults to |
HSROC |
if |
specrange |
A numeric vector of length 2 giving the range of
specificities over which the HSROC curve is plotted.
Defaults to |
conflevel |
Confidence level for the confidence region. Default is |
predlevel |
Confidence level for the prediction region. Default is |
studyCI |
Whether study-level confidence
intervals should be displayed for the observed sensitivity and
specificity estimates. Defaults to |
studylabels |
Whether study identifiers should
be displayed next to the study-level estimates. Defaults to
|
legend |
Whether a legend should be displayed. Default is |
... |
Additional graphical arguments passed to plotting functions. |
The plot is constructed on the ROC scale with sensitivity on the y-axis and specificity on the x-axis (displayed as 1 - false positive rate on a reversed axis).
Study-specific estimates are shown using the selected symbol (rectangles by default).
The following elements are displayed:
Study-level sensitivity and specificity estimates (Empirical Bayes Estimates)
Summary (pooled) estimate
confidence region around the summary point
prediction region reflecting between-study variability
Optional HSROC curve (if HSROC = TRUE)
Confidence and prediction regions are derived using the delta method based on the estimated variance-covariance structure of the model.
No return value. Called for its side effect of producing a plot.
Liu, Y., Chen, Y., & Chu, H. (2015). A unification of models for meta-analysis of diagnostic accuracy studies without a gold standard. Biometrics, 71(2), 538-547. doi:10.1111/biom.12264
Freeman, S. C., Kerby, C. R., Patel, A., Cooper, N. J., Quinn, T., & Sutton, A. J. (2019). Development of an interactive web-based tool to conduct and interrogate meta-analysis of diagnostic test accuracy studies: MetaDTA. BMC Medical Research Methodology, 19, 81. doi:10.1186/s12874-019-0724-x
Harbord, R. M., Deeks, J. J., Egger, M., Whiting, P., & Sterne, J. A. C. (2007). A unification of models for meta-analysis of diagnostic accuracy studies. Biostatistics, 8(2), 239–251. doi:10.1093/biostatistics/kxl004
Produces a summary ROC plot for objects of class "ReitsmaSubgroup"
obtained from fitReitsmaSubgroup. The plot displays study-level
estimates of sensitivity and specificity, the summary operating point,
and corresponding confidence and prediction regions. Optionally, the
HSROC (hierarchical summary ROC) curve can be overlaid.
## S3 method for class 'ReitsmaSubgroup' plot( x, symbol = NULL, scale = 0.02, size = c("equal", "fisher", "fisher_revman", "sampsize", "se", "sampsize_revman", "se_revman"), main = "Diagnostic Test Accuracy Meta-Analysis", col = NULL, nudge_legend = -0.4, HSROC = FALSE, specrange = c(0.7, 0.995), conflevel = 0.95, predlevel = 0.95, connectstudies = FALSE, studyCI = FALSE, studylabels = FALSE, legend = TRUE, ... )## S3 method for class 'ReitsmaSubgroup' plot( x, symbol = NULL, scale = 0.02, size = c("equal", "fisher", "fisher_revman", "sampsize", "se", "sampsize_revman", "se_revman"), main = "Diagnostic Test Accuracy Meta-Analysis", col = NULL, nudge_legend = -0.4, HSROC = FALSE, specrange = c(0.7, 0.995), conflevel = 0.95, predlevel = 0.95, connectstudies = FALSE, studyCI = FALSE, studylabels = FALSE, legend = TRUE, ... )
x |
An object of class |
symbol |
Character vector specifying the symbols used for study-level
estimates of the subgroups. One can choose |
scale |
Numeric scaling factor controlling study-symbol dimensions.
The default is |
size |
Character string controlling display of study-level point estimates:
|
main |
Character string giving the main title of the plot.
Defaults to |
col |
Vector of colours used for subgroup-specific HSROC curves,
study-level point estimates, summary points, confidence and prediction region.
If |
nudge_legend |
Numeric horizontal offset for the subgroup legend.
More negative values move the legend further right, outside the plotting area.
Values closer to zero move it closer to the panel. Default is |
HSROC |
if |
specrange |
A numeric vector of length 2 giving the range of
specificities over which the HSROC curve is plotted.
Defaults to |
conflevel |
Confidence level for the confidence region. Default is |
predlevel |
Confidence level for the prediction region. Default is |
connectstudies |
Whether the point estimates of two subgroups
within the same study should be connected. Defaults to |
studyCI |
Whether study-level confidence
intervals should be displayed for the observed sensitivity and
specificity estimates. Defaults to |
studylabels |
Whether study identifiers should
be displayed next to the study-level estimates. Defaults to
|
legend |
Whether a legend should be displayed. Default is |
... |
Additional graphical arguments passed to plotting functions. |
The plot is constructed on the ROC scale with sensitivity on the y-axis and specificity on the x-axis (displayed as 1 - false positive rate on a reversed axis).
Study-specific estimates are shown with subgroup-specific symbols and colours.
The following elements are displayed:
Study-level sensitivity and specificity estimates
Summary (pooled) estimate
confidence region around the summary point
prediction region reflecting between-study variability
Optional HSROC curve (if HSROC = TRUE)
Confidence and prediction regions are derived using the delta method based on the estimated variance-covariance structure of the model.
No return value. Called for its side effect of producing a plot.
Freeman, S. C., Kerby, C. R., Patel, A., Cooper, N. J., Quinn, T., & Sutton, A. J. (2019). Development of an interactive web-based tool to conduct and interrogate meta-analysis of diagnostic test accuracy studies: MetaDTA. BMC Medical Research Methodology, 19, 81. doi:10.1186/s12874-019-0724-x
Harbord, R. M., Deeks, J. J., Egger, M., Whiting, P., & Sterne, J. A. C. (2007). A unification of models for meta-analysis of diagnostic accuracy studies. Biostatistics, 8(2), 239–251. doi:10.1093/biostatistics/kxl004
Riley, R. D., Ensor, J., Jackson, D., & Burke, D. L. (2018). Deriving percentage study weights in multi-parameter meta-analysis models: with application to meta-regression, network meta-analysis and one-stage individual participant data models. Statistical Methods in Medical Research, 27(10), 2885–2905. doi:10.1177/0962280216688033
Produces a summary ROC plot for objects of class "ReitsmaSubgroupLCA"
obtained from fitReitsmaSubgroupLCA. Study-specific sensitivities and
specificities are empirical Bayes estimates derived from the fitted latent
class model.
## S3 method for class 'ReitsmaSubgroupLCA' plot( x, symbol = NULL, scale = 0.02, size = c("eb", "equal", "sampsize", "eb_revman", "sampsize_revman"), main = "Diagnostic Test Accuracy Meta-Analysis", col = NULL, nudge_legend = -0.4, HSROC = FALSE, specrange = c(0.7, 0.995), conflevel = 0.95, predlevel = 0.95, connectstudies = FALSE, studyCI = FALSE, studylabels = FALSE, legend = TRUE, ... )## S3 method for class 'ReitsmaSubgroupLCA' plot( x, symbol = NULL, scale = 0.02, size = c("eb", "equal", "sampsize", "eb_revman", "sampsize_revman"), main = "Diagnostic Test Accuracy Meta-Analysis", col = NULL, nudge_legend = -0.4, HSROC = FALSE, specrange = c(0.7, 0.995), conflevel = 0.95, predlevel = 0.95, connectstudies = FALSE, studyCI = FALSE, studylabels = FALSE, legend = TRUE, ... )
x |
An object of class |
symbol |
Character vector specifying the symbols used for study-level
estimates of the subgroups. One can choose |
scale |
Numeric scaling factor controlling study-symbol dimensions.
The default is |
size |
Character string controlling display of study-level point estimates:
|
main |
Character string giving the main title of the plot.
Defaults to |
col |
Vector of colours used for subgroup-specific HSROC curves,
study-level point estimates, summary points, confidence and prediction region.
If |
nudge_legend |
Numeric horizontal offset for the subgroup legend.
More negative values move the legend further right, outside the plotting area.
Values closer to zero move it closer to the panel. Default is |
HSROC |
if |
specrange |
A numeric vector of length 2 giving the range of
specificities over which the HSROC curve is plotted.
Defaults to |
conflevel |
Confidence level for the confidence region. Default is |
predlevel |
Confidence level for the prediction region. Default is |
connectstudies |
Whether the point estimates of two subgroups
within the same study should be connected. Defaults to |
studyCI |
Whether study-level confidence
intervals should be displayed for the observed sensitivity and
specificity estimates. Defaults to |
studylabels |
Whether study identifiers should
be displayed next to the study-level estimates. Defaults to
|
legend |
Whether a legend should be displayed. Default is |
... |
Additional graphical arguments passed to plotting functions. |
The plot is constructed on the ROC scale with sensitivity on the y-axis and specificity on the x-axis (displayed as 1 - false positive rate on a reversed axis).
Study-specific estimates are shown with subgroup-specific symbols and colours.
The following elements are displayed:
Study-level sensitivity and specificity estimates
Summary (pooled) estimate
confidence region around the summary point
prediction region reflecting between-study variability
Optional HSROC curve (if HSROC = TRUE)
Confidence and prediction regions are derived using the delta method based on the estimated variance-covariance structure of the model.
No return value. Called for its side effect of producing a plot.
Liu, Y., Chen, Y., & Chu, H. (2015). A unification of models for meta-analysis of diagnostic accuracy studies without a gold standard. Biometrics, 71(2), 538-547. doi:10.1111/biom.12264
Freeman, S. C., Kerby, C. R., Patel, A., Cooper, N. J., Quinn, T., & Sutton, A. J. (2019). Development of an interactive web-based tool to conduct and interrogate meta-analysis of diagnostic test accuracy studies: MetaDTA. BMC Medical Research Methodology, 19, 81. doi:10.1186/s12874-019-0724-x
Harbord, R. M., Deeks, J. J., Egger, M., Whiting, P., & Sterne, J. A. C. (2007). A unification of models for meta-analysis of diagnostic accuracy studies. Biostatistics, 8(2), 239–251. doi:10.1093/biostatistics/kxl004
Produces a summary ROC plot for objects of class "ReitsmaSubgroupTMB"
obtained from fitReitsmaSubgroupTMB. The plot displays study-level
estimates of sensitivity and specificity, the summary operating point,
and corresponding confidence and prediction regions. Optionally, the
HSROC (hierarchical summary ROC) curve can be overlaid.
## S3 method for class 'ReitsmaSubgroupTMB' plot( x, symbol = NULL, scale = 0.02, size = c("equal", "fisher", "fisher_revman", "sampsize", "se", "sampsize_revman", "se_revman"), main = "Diagnostic Test Accuracy Meta-Analysis", col = NULL, nudge_legend = -0.4, HSROC = FALSE, specrange = c(0.7, 0.995), conflevel = 0.95, predlevel = 0.95, connectstudies = FALSE, studyCI = FALSE, studylabels = FALSE, legend = TRUE, ... )## S3 method for class 'ReitsmaSubgroupTMB' plot( x, symbol = NULL, scale = 0.02, size = c("equal", "fisher", "fisher_revman", "sampsize", "se", "sampsize_revman", "se_revman"), main = "Diagnostic Test Accuracy Meta-Analysis", col = NULL, nudge_legend = -0.4, HSROC = FALSE, specrange = c(0.7, 0.995), conflevel = 0.95, predlevel = 0.95, connectstudies = FALSE, studyCI = FALSE, studylabels = FALSE, legend = TRUE, ... )
x |
An object of class |
symbol |
Character vector specifying the symbols used for study-level
estimates of the subgroups. One can choose |
scale |
Numeric scaling factor controlling study-symbol dimensions.
The default is |
size |
Character string controlling display of study-level point estimates:
|
main |
Character string giving the main title of the plot.
Defaults to |
col |
Vector of colours used for subgroup-specific HSROC curves,
study-level symbols, summary points, confidence and prediction region.
If |
nudge_legend |
Numeric horizontal offset for the subgroup legend.
More negative values move the legend further right, outside the plotting area.
Values closer to zero move it closer to the panel. Default is |
HSROC |
if |
specrange |
A numeric vector of length 2 giving the range of
specificities over which the HSROC curve is plotted.
Defaults to |
conflevel |
Confidence level for the confidence region. Default is |
predlevel |
Confidence level for the prediction region. Default is |
connectstudies |
Whether the point estimates of two subgroups
within the same study should be connected. Defaults to |
studyCI |
Whether study-level confidence
intervals should be displayed for the observed sensitivity and
specificity estimates. Defaults to |
studylabels |
Whether study identifiers should
be displayed next to the study-level estimates. Defaults to
|
legend |
Whether a legend should be displayed. Default is |
... |
Additional graphical arguments passed to plotting functions. |
The plot is constructed on the ROC scale with sensitivity on the y-axis and specificity on the x-axis (displayed as 1 - false positive rate on a reversed axis).
Study-specific estimates are shown with study-specific symbols and colours.
The following elements are displayed:
Study-level sensitivity and specificity estimates
Summary (pooled) estimate
confidence region around the summary point
prediction region reflecting between-study variability
Optional HSROC curve (if HSROC = TRUE)
Confidence and prediction regions are derived using the delta method based on the estimated variance-covariance structure of the model.
No return value. Called for its side effect of producing a plot.
Harbord, R. M., Deeks, J. J., Egger, M., Whiting, P., & Sterne, J. A. C. (2007). A unification of models for meta-analysis of diagnostic accuracy studies. Biostatistics, 8(2), 239–251. doi:10.1093/biostatistics/kxl004
Produces a summary ROC plot for objects of class "ReitsmaTMB"
obtained from fitReitsmaTMB. The plot displays study-level
estimates of sensitivity and specificity, the summary operating point,
and corresponding confidence and prediction regions. Optionally, the
HSROC (hierarchical summary ROC) curve can be overlaid.
## S3 method for class 'ReitsmaTMB' plot( x, symbol = c("rectangle", "ellipse", "diamond", "triangle", "cross", "plus", "star"), scale = 0.02, size = c("fisher", "fisher_revman", "equal", "sampsize", "se", "sampsize_revman", "se_revman"), main = "Diagnostic Test Accuracy Meta-Analysis", HSROC = FALSE, specrange = c(0.7, 0.995), conflevel = 0.95, predlevel = 0.95, studyCI = FALSE, studylabels = FALSE, legend = TRUE, ... )## S3 method for class 'ReitsmaTMB' plot( x, symbol = c("rectangle", "ellipse", "diamond", "triangle", "cross", "plus", "star"), scale = 0.02, size = c("fisher", "fisher_revman", "equal", "sampsize", "se", "sampsize_revman", "se_revman"), main = "Diagnostic Test Accuracy Meta-Analysis", HSROC = FALSE, specrange = c(0.7, 0.995), conflevel = 0.95, predlevel = 0.95, studyCI = FALSE, studylabels = FALSE, legend = TRUE, ... )
x |
An object of class |
symbol |
Character string specifying the symbol used for study-level
estimates. One of |
scale |
Numeric scaling factor controlling study-symbol dimensions.
The default is |
size |
Character string controlling display of study-level point estimates:
|
main |
Character string giving the main title of the plot.
Defaults to |
HSROC |
If |
specrange |
A numeric vector of length 2 giving the range of
specificities over which the HSROC curve is plotted.
Defaults to |
conflevel |
Confidence level for the confidence region. Default is |
predlevel |
Confidence level for the prediction region. Default is |
studyCI |
Whether study-level confidence
intervals should be displayed for the observed sensitivity and
specificity estimates. Defaults to |
studylabels |
Whether study identifiers should
be displayed next to the study-level estimates. Defaults to
|
legend |
Whether a legend should be displayed. Default is |
... |
Additional graphical arguments passed to plotting functions. |
The plot is constructed on the ROC scale with sensitivity on the y-axis and specificity on the x-axis (displayed as 1 - false positive rate on a reversed axis).
Study-specific estimates are shown using the selected symbol (rectangles by default).
The following elements are displayed:
Study-level sensitivity and specificity estimates
Summary (pooled) estimate
confidence region around the summary point
prediction region reflecting between-study variability
Optional HSROC curve (if HSROC = TRUE)
Confidence and prediction regions are derived using the delta method based on the estimated variance-covariance structure of the model.
No return value. Called for its side effect of producing a plot.
Freeman, S. C., Kerby, C. R., Patel, A., Cooper, N. J., Quinn, T., & Sutton, A. J. (2019). Development of an interactive web-based tool to conduct and interrogate meta-analysis of diagnostic test accuracy studies: MetaDTA. BMC Medical Research Methodology, 19, 81. doi:10.1186/s12874-019-0724-x
Harbord, R. M., Deeks, J. J., Egger, M., Whiting, P., & Sterne, J. A. C. (2007). A unification of models for meta-analysis of diagnostic accuracy studies. Biostatistics, 8(2), 239–251. doi:10.1093/biostatistics/kxl004
Produces a summary ROC plot for objects of class "RutterGatsonis"
obtained from fitRutterGatsonis. The plot displays study-level
estimates of sensitivity and specificity and the
HSROC (hierarchical summary ROC).
## S3 method for class 'RutterGatsonis' plot( x, symbol = c("rectangle", "ellipse", "diamond", "triangle", "cross", "plus", "star"), scale = 0.02, size = c("fisher", "fisher_revman", "equal", "sampsize", "se", "sampsize_revman", "se_revman"), specrange = c(0.7, 0.995), main = "Diagnostic Test Accuracy Meta-Analysis", HSROC = TRUE, conflevel = 0.95, studyCI = FALSE, studylabels = FALSE, legend = TRUE, ... )## S3 method for class 'RutterGatsonis' plot( x, symbol = c("rectangle", "ellipse", "diamond", "triangle", "cross", "plus", "star"), scale = 0.02, size = c("fisher", "fisher_revman", "equal", "sampsize", "se", "sampsize_revman", "se_revman"), specrange = c(0.7, 0.995), main = "Diagnostic Test Accuracy Meta-Analysis", HSROC = TRUE, conflevel = 0.95, studyCI = FALSE, studylabels = FALSE, legend = TRUE, ... )
x |
An object of class |
symbol |
Character string specifying the symbol used for study-level
estimates. One of |
scale |
Numeric scaling factor controlling study-symbol dimensions.
The default is |
size |
Character string controlling display of study-level point estimates:
|
specrange |
A numeric vector of length 2 giving the range of
specificities over which the HSROC curve is plotted.
Defaults to |
main |
Character string giving the main title of the plot.
Defaults to |
HSROC |
if |
conflevel |
Confidence level for the study-level confidence
intervals. Default is |
studyCI |
Whether study-level confidence
intervals should be displayed for the observed sensitivity and
specificity estimates. Defaults to |
studylabels |
Whether study identifiers should
be displayed next to the study-level estimates. Defaults to
|
legend |
Whether a legend should be displayed. Default is |
... |
Additional graphical arguments passed to plotting functions. |
The plot is constructed on the ROC scale with sensitivity on the y-axis and specificity on the x-axis (displayed as 1 - false positive rate on a reversed axis).
Study-specific estimates are shown using the selected symbol (rectangles by default).
The following elements are displayed:
Study-level sensitivity and specificity estimates
HSROC curve
No return value. Called for its side effect of producing a plot.
Freeman, S. C., Kerby, C. R., Patel, A., Cooper, N. J., Quinn, T., & Sutton, A. J. (2019). Development of an interactive web-based tool to conduct and interrogate meta-analysis of diagnostic test accuracy studies: MetaDTA. BMC Medical Research Methodology, 19, 81. doi:10.1186/s12874-019-0724-x
Produces a summary ROC plot for objects of class "RutterGatsonisLCA"
obtained from fitRutterGatsonisLCA. Study-specific sensitivities and
specificities are empirical Bayes estimates derived from the fitted latent
class model.
## S3 method for class 'RutterGatsonisLCA' plot( x, symbol = c("rectangle", "ellipse", "diamond", "triangle", "cross", "plus", "star"), scale = 0.02, size = c("eb", "equal", "sampsize", "eb_revman", "sampsize_revman"), specrange = c(0.7, 0.995), main = "Diagnostic Test Accuracy Meta-Analysis", HSROC = TRUE, studyCI = FALSE, conflevel = 0.95, studylabels = FALSE, legend = TRUE, ... )## S3 method for class 'RutterGatsonisLCA' plot( x, symbol = c("rectangle", "ellipse", "diamond", "triangle", "cross", "plus", "star"), scale = 0.02, size = c("eb", "equal", "sampsize", "eb_revman", "sampsize_revman"), specrange = c(0.7, 0.995), main = "Diagnostic Test Accuracy Meta-Analysis", HSROC = TRUE, studyCI = FALSE, conflevel = 0.95, studylabels = FALSE, legend = TRUE, ... )
x |
An object of class |
symbol |
Character string specifying the symbol used for study-level
estimates. One of |
scale |
Numeric scaling factor controlling study-symbol dimensions.
The default is |
size |
Character string controlling display of study-level point estimates:
|
specrange |
A numeric vector of length 2 giving the range of
specificities over which the HSROC curve is plotted.
Defaults to |
main |
Character string giving the main title of the plot.
Defaults to |
HSROC |
if |
studyCI |
Whether study-level confidence
intervals should be displayed for the observed sensitivity and
specificity estimates. Defaults to |
conflevel |
Confidence level for the study-level confidence
intervals. Default is |
studylabels |
Whether study identifiers should
be displayed next to the study-level estimates. Defaults to
|
legend |
Whether a legend should be displayed. Default is |
... |
Additional graphical arguments passed to plotting functions. |
The plot is constructed on the ROC scale with sensitivity on the y-axis and specificity on the x-axis (displayed as 1 - false positive rate on a reversed axis).
Study-specific estimates are shown using the selected symbol (rectangles by default).
The following elements are displayed:
Study-level sensitivity and specificity estimates
HSROC curve
No return value. Called for its side effect of producing a plot.
Liu, Y., Chen, Y., & Chu, H. (2015). A unification of models for meta-analysis of diagnostic accuracy studies without a gold standard. Biometrics, 71(2), 538-547. doi:10.1111/biom.12264
Freeman, S. C., Kerby, C. R., Patel, A., Cooper, N. J., Quinn, T., & Sutton, A. J. (2019). Development of an interactive web-based tool to conduct and interrogate meta-analysis of diagnostic test accuracy studies: MetaDTA. BMC Medical Research Methodology, 19, 81. doi:10.1186/s12874-019-0724-x
Produces summary ROC plots for objects of class "RutterGatsonisSubgroup"
obtained from fitRutterGatsonisSubgroup. The plot displays
study-level estimates of sensitivity and specificity, stratified by subgroup,
together with subgroup-specific HSROC (hierarchical summary ROC) curves.
## S3 method for class 'RutterGatsonisSubgroup' plot( x, symbol = NULL, scale = 0.02, size = c("equal", "fisher", "fisher_revman", "sampsize", "se", "sampsize_revman", "se_revman"), nudge_legend = -0.4, specrange = c(0.7, 0.995), col = NULL, main = "Diagnostic Test Accuracy Meta-Analysis", HSROC = TRUE, connectstudies = FALSE, studyCI = FALSE, conflevel = 0.95, studylabels = FALSE, legend = TRUE, ... )## S3 method for class 'RutterGatsonisSubgroup' plot( x, symbol = NULL, scale = 0.02, size = c("equal", "fisher", "fisher_revman", "sampsize", "se", "sampsize_revman", "se_revman"), nudge_legend = -0.4, specrange = c(0.7, 0.995), col = NULL, main = "Diagnostic Test Accuracy Meta-Analysis", HSROC = TRUE, connectstudies = FALSE, studyCI = FALSE, conflevel = 0.95, studylabels = FALSE, legend = TRUE, ... )
x |
An object of class |
symbol |
Character vector specifying the symbols used for study-level
estimates of the subgroups. One can choose |
scale |
Numeric scaling factor controlling study-symbol dimensions.
The default is |
size |
Character string controlling display of study-level point estimates:
|
nudge_legend |
Numeric horizontal offset for the subgroup legend.
More negative values move the legend further right, outside the plotting area.
Values closer to zero move it closer to the panel. Default is |
specrange |
A numeric vector of length 2 giving the range of
specificities over which the HSROC curve is plotted.
Defaults to |
col |
Vector of colours used for subgroup-specific HSROC curves
and study-level point estimates. If |
main |
Character string giving the main title of the plot.
Defaults to |
HSROC |
if |
connectstudies |
Whether the point estimates of two subgroups
within the same study should be connected. Defaults to |
studyCI |
Whether study-level confidence
intervals should be displayed for the observed sensitivity and
specificity estimates. Defaults to |
conflevel |
Confidence level for the study-level confidence
intervals. Default is |
studylabels |
Whether study identifiers should
be displayed next to the study-level estimates. Defaults to
|
legend |
Whether a legend should be displayed. Default is |
... |
Additional graphical arguments passed to plotting functions. |
The plot is constructed on the ROC scale with sensitivity on the y-axis and specificity on the x-axis (displayed as 1 - false positive rate on a reversed axis).
Study-specific estimates are shown with subgroup-specific symbols and colours.
The following elements are displayed:
Study-level sensitivity and specificity estimates by subgroup
Subgroup-specific HSROC curves
A legend identifying the subgroups
No return value. Called for its side effect of producing a plot.
Freeman, S. C., Kerby, C. R., Patel, A., Cooper, N. J., Quinn, T., & Sutton, A. J. (2019). Development of an interactive web-based tool to conduct and interrogate meta-analysis of diagnostic test accuracy studies: MetaDTA. BMC Medical Research Methodology, 19, 81. doi:10.1186/s12874-019-0724-x
Produces summary ROC plots for objects of class "RutterGatsonisSubgroupLCA"
obtained from fitRutterGatsonisSubgroupLCA. The plot displays
study-level estimates of sensitivity and specificity (empirical Bayes estimates), stratified by subgroup,
together with subgroup-specific HSROC (hierarchical summary ROC) curves.
## S3 method for class 'RutterGatsonisSubgroupLCA' plot( x, symbol = NULL, scale = 0.02, size = c("eb", "equal", "sampsize", "eb_revman", "sampsize_revman"), nudge_legend = -0.4, specrange = c(0.7, 0.995), col = NULL, main = "Diagnostic Test Accuracy Meta-Analysis", HSROC = TRUE, connectstudies = FALSE, studyCI = FALSE, conflevel = 0.95, studylabels = FALSE, legend = TRUE, ... )## S3 method for class 'RutterGatsonisSubgroupLCA' plot( x, symbol = NULL, scale = 0.02, size = c("eb", "equal", "sampsize", "eb_revman", "sampsize_revman"), nudge_legend = -0.4, specrange = c(0.7, 0.995), col = NULL, main = "Diagnostic Test Accuracy Meta-Analysis", HSROC = TRUE, connectstudies = FALSE, studyCI = FALSE, conflevel = 0.95, studylabels = FALSE, legend = TRUE, ... )
x |
An object of class |
symbol |
Character vector specifying the symbols used for study-level
estimates of the subgroups. One can choose |
scale |
Numeric scaling factor controlling study-symbol dimensions.
The default is |
size |
Character string controlling display of study-level point estimates:
|
nudge_legend |
Numeric horizontal offset for the subgroup legend.
More negative values move the legend further right, outside the plotting area.
Values closer to zero move it closer to the panel. Default is |
specrange |
A numeric vector of length 2 giving the range of
specificities over which the HSROC curve is plotted.
Defaults to |
col |
Vector of colours used for subgroup-specific HSROC curves
and study-level point estimates. If |
main |
Character string giving the main title of the plot.
Defaults to |
HSROC |
if |
connectstudies |
Whether the point estimates of two subgroups
within the same study should be connected. Defaults to |
studyCI |
Whether study-level confidence
intervals should be displayed for the observed sensitivity and
specificity estimates. Defaults to |
conflevel |
Confidence level for the study-level confidence
intervals. Default is |
studylabels |
Whether study identifiers should
be displayed next to the study-level estimates. Defaults to
|
legend |
Whether a legend should be displayed. Default is |
... |
Additional graphical arguments passed to plotting functions. |
The plot is constructed on the ROC scale with sensitivity on the y-axis and specificity on the x-axis (displayed as 1 - false positive rate on a reversed axis).
Study-specific estimates are shown with subgroup-specific symbols and colours.
The following elements are displayed:
Study-level sensitivity and specificity estimates by subgroup
Subgroup-specific HSROC curves
A legend identifying the subgroups
No return value. Called for its side effect of producing a plot.
Liu, Y., Chen, Y., & Chu, H. (2015). A unification of models for meta-analysis of diagnostic accuracy studies without a gold standard. Biometrics, 71(2), 538-547. doi:10.1111/biom.12264
Freeman, S. C., Kerby, C. R., Patel, A., Cooper, N. J., Quinn, T., & Sutton, A. J. (2019). Development of an interactive web-based tool to conduct and interrogate meta-analysis of diagnostic test accuracy studies: MetaDTA. BMC Medical Research Methodology, 19, 81. doi:10.1186/s12874-019-0724-x
Harbord, R. M., Deeks, J. J., Egger, M., Whiting, P., & Sterne, J. A. C. (2007). A unification of models for meta-analysis of diagnostic accuracy studies. Biostatistics, 8(2), 239–251. doi:10.1093/biostatistics/kxl004
Displays a concise summary of a fitted Hoyer AFT model, including distribution, number of studies, convergence status, and likelihood-based fit statistics.
## S3 method for class 'HoyerAFT' print(x, ...)## S3 method for class 'HoyerAFT' print(x, ...)
x |
An object of class |
... |
Further arguments (unused). |
Invisibly returns the input object.
Displays a concise summary of a fitted Reitsma diagnostic test accuracy model, including number of studies, convergence status and likelihood-based fit statistics.
## S3 method for class 'Reitsma' print(x, ...)## S3 method for class 'Reitsma' print(x, ...)
x |
An object of class |
... |
Additional arguments (unused). |
Invisibly returns the input object.
Displays a concise summary of a fitted Reitsma LCA model, including number of studies, convergence status, and likelihood-based fit statistics.
## S3 method for class 'ReitsmaLCA' print(x, ...)## S3 method for class 'ReitsmaLCA' print(x, ...)
x |
An object of class |
... |
Additional arguments (unused). |
Invisibly returns the input object.
Displays a concise summary of a fitted Reitsma Subgroup diagnostic test accuracy model, including number of studies, convergence status, and likelihood-based fit statistics.
## S3 method for class 'ReitsmaSubgroup' print(x, ...)## S3 method for class 'ReitsmaSubgroup' print(x, ...)
x |
An object of class |
... |
Additional arguments (unused). |
Invisibly returns the input object.
Displays a concise summary of a fitted ReitsmaSubgroupLCA model, including number of studies, convergence status, and likelihood-based fit statistics.
## S3 method for class 'ReitsmaSubgroupLCA' print(x, ...)## S3 method for class 'ReitsmaSubgroupLCA' print(x, ...)
x |
An object of class |
... |
Additional arguments (unused). |
Invisibly returns the input object.
Displays a concise summary of a fitted ReitsmaSubgroupTMB diagnostic test accuracy model, including number of studies, convergence status and likelihood-based fit statistics.
## S3 method for class 'ReitsmaSubgroupTMB' print(x, ...)## S3 method for class 'ReitsmaSubgroupTMB' print(x, ...)
x |
An object of class |
... |
Additional arguments (unused). |
Invisibly returns the input object.
Displays a concise summary of a fitted ReitsmaTMB diagnostic test accuracy model, including number of studies, convergence status and likelihood-based fit statistics.
## S3 method for class 'ReitsmaTMB' print(x, ...)## S3 method for class 'ReitsmaTMB' print(x, ...)
x |
An object of class |
... |
Additional arguments (unused). |
Invisibly returns the input object.
Displays a concise summary of a fitted HSROC model, including number of studies, convergence status, and likelihood-based fit statistics.
## S3 method for class 'RutterGatsonis' print(x, ...)## S3 method for class 'RutterGatsonis' print(x, ...)
x |
An object of class |
... |
Additional arguments (unused). |
Invisibly returns the input object.
Displays a concise summary of a fitted HSROC LCA model, including number of studies, convergence status, and likelihood-based fit statistics.
## S3 method for class 'RutterGatsonisLCA' print(x, ...)## S3 method for class 'RutterGatsonisLCA' print(x, ...)
x |
An object of class |
... |
Additional arguments (unused). |
Invisibly returns the input object.
Displays a concise summary of a fitted HSROC model, including number of studies, convergence status, and likelihood-based fit statistics.
## S3 method for class 'RutterGatsonisReg' print(x, ...)## S3 method for class 'RutterGatsonisReg' print(x, ...)
x |
An object of class |
... |
Additional arguments (unused). |
Invisibly returns the input object.
Displays a concise summary of a fitted HSROC model, including number of studies, convergence status, and likelihood-based fit statistics.
## S3 method for class 'RutterGatsonisSubgroup' print(x, ...)## S3 method for class 'RutterGatsonisSubgroup' print(x, ...)
x |
An object of class |
... |
Additional arguments (unused). |
Invisibly returns the input object.
summary.RutterGatsonisSubgroup
Displays a concise summary of a fitted RutterGatsonisSubgroupLCA model, including number of studies, convergence status, and likelihood-based fit statistics.
## S3 method for class 'RutterGatsonisSubgroupLCA' print(x, ...)## S3 method for class 'RutterGatsonisSubgroupLCA' print(x, ...)
x |
An object of class |
... |
Additional arguments (unused). |
Invisibly returns the input object.
summary.RutterGatsonisSubgroupLCA
Prints summary objects returned by
summary() methods for diagnostic
test accuracy models.
## S3 method for class 'summary.DTAmodel' print(x, digits = max(8L, getOption("digits") - 8L), ...) ## S3 method for class 'summary.HoyerAFT' print(x, digits = max(8L, getOption("digits") - 8L), ...) ## S3 method for class 'summary.Reitsma' print(x, digits = max(8L, getOption("digits") - 8L), ...) ## S3 method for class 'summary.ReitsmaTMB' print(x, digits = max(8L, getOption("digits") - 8L), ...) ## S3 method for class 'summary.ReitsmaLCA' print(x, digits = max(8L, getOption("digits") - 8L), ...) ## S3 method for class 'summary.ReitsmaSubgroup' print(x, digits = max(8L, getOption("digits") - 8L), ...) ## S3 method for class 'summary.ReitsmaSubgroupTMB' print(x, digits = max(8L, getOption("digits") - 8L), ...) ## S3 method for class 'summary.ReitsmaSubgroupLCA' print(x, digits = max(8L, getOption("digits") - 8L), ...) ## S3 method for class 'summary.RutterGatsonis' print(x, digits = max(8L, getOption("digits") - 8L), ...) ## S3 method for class 'summary.RutterGatsonisReg' print(x, digits = max(8L, getOption("digits") - 8L), ...) ## S3 method for class 'summary.RutterGatsonisLCA' print(x, digits = max(8L, getOption("digits") - 8L), ...) ## S3 method for class 'summary.RutterGatsonisSubgroup' print(x, digits = max(8L, getOption("digits") - 8L), ...) ## S3 method for class 'summary.RutterGatsonisSubgroupLCA' print(x, digits = max(8L, getOption("digits") - 8L), ...)## S3 method for class 'summary.DTAmodel' print(x, digits = max(8L, getOption("digits") - 8L), ...) ## S3 method for class 'summary.HoyerAFT' print(x, digits = max(8L, getOption("digits") - 8L), ...) ## S3 method for class 'summary.Reitsma' print(x, digits = max(8L, getOption("digits") - 8L), ...) ## S3 method for class 'summary.ReitsmaTMB' print(x, digits = max(8L, getOption("digits") - 8L), ...) ## S3 method for class 'summary.ReitsmaLCA' print(x, digits = max(8L, getOption("digits") - 8L), ...) ## S3 method for class 'summary.ReitsmaSubgroup' print(x, digits = max(8L, getOption("digits") - 8L), ...) ## S3 method for class 'summary.ReitsmaSubgroupTMB' print(x, digits = max(8L, getOption("digits") - 8L), ...) ## S3 method for class 'summary.ReitsmaSubgroupLCA' print(x, digits = max(8L, getOption("digits") - 8L), ...) ## S3 method for class 'summary.RutterGatsonis' print(x, digits = max(8L, getOption("digits") - 8L), ...) ## S3 method for class 'summary.RutterGatsonisReg' print(x, digits = max(8L, getOption("digits") - 8L), ...) ## S3 method for class 'summary.RutterGatsonisLCA' print(x, digits = max(8L, getOption("digits") - 8L), ...) ## S3 method for class 'summary.RutterGatsonisSubgroup' print(x, digits = max(8L, getOption("digits") - 8L), ...) ## S3 method for class 'summary.RutterGatsonisSubgroupLCA' print(x, digits = max(8L, getOption("digits") - 8L), ...)
x |
A summary object inheriting from
|
digits |
Number of significant digits used for printing. |
... |
Additional arguments passed to printing methods. |
Invisibly returns x.
Transforms study-level diagnostic test accuracy (DTA) data with multiple thresholds into interval-censored format suitable for likelihood-based modelling (Hoyer et al., 2018).
restructure_data( data, TP, FP, FN, TN, threshold, study, smallest, largest, testdirection = c("greater", "less") )restructure_data( data, TP, FP, FN, TN, threshold, study, smallest, largest, testdirection = c("greater", "less") )
data |
A data.frame containing study-level data. |
TP |
True positives (column name). |
FP |
False positives (column name). |
FN |
False negatives (column name). |
TN |
True negatives (column name). |
threshold |
The observed threshold value (column name). Must be positive and strictly increasing within each study. |
study |
Study identifier (column name). |
smallest |
Positive lower bound used to define the
leftmost interval. Must be smaller than minimum |
largest |
Positive upper bound used to define the
rightmost interval. Must be greater than maximum |
testdirection |
Direction of the test. Enter |
The function constructs:
A left-censored interval (below the first threshold)
Intermediate intervals between adjacent thresholds
A right-censored interval (above the last threshold)
Event counts are derived from cumulative counts to represent the number of observations falling within each interval for diseased and non-diseased groups. Therefore, input counts must be cumulative over increasing thresholds within each study.
The function first validates that counts are numeric, non-negative integers and that threshold values are positive.
Within each study, total numbers of diseased (n1) and
non-diseased (n0) individuals are required to be constant across
thresholds. Intermediate interval counts are computed as differences
between cumulative counts.
The log-scale midpoint (lcutmean) is provided to support
initialization of random effects in subsequent Hoyer AFT models.
For testdirection = "greater", the function assumes that sensitivity
decreases and specificity increases with increasing thresholds. For
testdirection = "less", the reverse monotonicity is required.
Internally, the function standardizes the definition of a positive test
result so that it always corresponds to values above the threshold. For
testdirection = "less", this is achieved by relabeling the observed
counts. This does not affect the resulting sensitivity, specificity, or ROC
curve, but ensures compatibility with the model formulation.
A list with two components:
A data frame with one row per constructed interval containing:
Study identifier
Original counts carried forward
Threshold associated with the interval
Lower interval bound (NA for left-censored)
Upper interval bound (NA for right-censored)
Number of diseased observations in the interval
Number of non-diseased observations in the interval
Censoring type (1 = left, 2 = interval, 3 = right)
Midpoint of log-thresholds defining the interval
The processed original data including (derived) quantities:
Total number of diseased individuals (TP + FN)
Total number of non-diseased individuals (TN + FP)
Sensitivity (TP / n1)
Specificity (TN / n0)
False positive rate (FP / n0)
As specified by testdirection
Hoyer, A., Hirt, S., Kuss, O. (2018). Meta-analysis of full ROC curves using bivariate time-to-event models for interval-censored data. Research Synthesis Methods, 9(1), 62-72. doi:10.1002/jrsm.1273
data("diabetes") res <- restructure_data( data = diabetes, TP = TP, FP = FP, FN = FN, TN = TN, threshold = threshold, study = study, smallest = 2, largest = 10 )data("diabetes") res <- restructure_data( data = diabetes, TP = TP, FP = FP, FN = FN, TN = TN, threshold = threshold, study = study, smallest = 2, largest = 10 )
This is the RF dataset from Nishimura (2007) from a review of rheumatoid factor (RF) to diagnose rheumatoid arthritis.
RFRF
A data frame with 50 rows and 8 variables:
Study identifier
Year of the study
Number of true positives
Number of false positives
Number of false negatives
Number of true negatives
Threshold used in U/mL for test positivity
Different methods used to perform the test
Nishimura, K. et al. (2007). Meta-analysis: diagnostic accuracy of anti-cyclic citrullinated peptide antibody and rheumatoid factor for rheumatoid arthritis. Annals of Internal Medicine, 146(11), 392-403. doi:10.7326/0003-4819-146-11-200706050-00008
This is the schuetz dataset from Schuetz (2010) from a meta-analysis of non-invasive coronary angiography using computer tomography (CT) versus magnetic resonance imaging (MRI)
schuetzschuetz
A data frame with 108 rows and 7 variables:
Which test was used, CT or MRI
Study identifier
Number of true positives
Number of false positives
Number of false negatives
Number of true negatives
whether the comparison is indirect (=1) or direct (=0)
Schuetz, K., et al. (2010). Meta‐analysis: noninvasive coronary angiography using computer tomography versus magnetic resonance imaging. Annals of Internal Medicine, 152(3), 167-177. doi:10.7326/0003-4819-152-3-201002020-00008
Extracts and returns the summary information stored in a fitted
HoyerAFT model object.
## S3 method for class 'HoyerAFT' summary(object, ...)## S3 method for class 'HoyerAFT' summary(object, ...)
object |
An object of class |
... |
Additional arguments (currently unused). |
This method is part of the standard S3 summary() generic and
provides access to summary statistics computed from the fitted model,
as stored in the sdreport2 and sensspec component of the object.
A list of class "summary.HoyerAFT" with two data frames containing summary statistics derived
from the fitted model.
sdreport2: Parameter estimates with standard errors as returned from TMB reported parameters.
sensspec: Estimated sensitivity and specificity with confidence intervals at the specified thresholds.
Extracts key results from an object of class "Reitsma", including
parameter estimates, sensitivity and specificity summaries, and recovered
HSROC parameters from the Rutter–Gatsonis parameterization.
## S3 method for class 'Reitsma' summary(object, ...)## S3 method for class 'Reitsma' summary(object, ...)
object |
An object of class |
... |
Additional arguments (currently ignored). |
A list of class "summary.Reitsma" with the following components:
estimates: Parameter estimates with standard errors.
sensspec: Estimated sensitivity and specificity with confidence intervals.
RutterGatsonis_recovered: Recovered parameters in the Rutter-Gatsonis (HSROC) parameterization.
Extracts key results from an object of class "ReitsmaLCA", including
parameter estimates, sensitivity and specificity summaries, and recovered
HSROC parameters from the Rutter–Gatsonis parameterization.
## S3 method for class 'ReitsmaLCA' summary(object, ...)## S3 method for class 'ReitsmaLCA' summary(object, ...)
object |
An object of class |
... |
Additional arguments (currently ignored). |
A list of class "summary.ReitsmaLCA" with the following components:
estimates: Parameter estimates with standard errors.
sensspec: Estimated sensitivity and specificity with confidence intervals.
prevref: Estimated (average) prevalence and reference standard sensitivity/specificity with confidence intervals.
RutterGatsonis_recovered: Recovered parameters in the Rutter-Gatsonis (HSROC) parameterization.
Extracts key results from an object of class "ReitsmaSubgroup", including
parameter estimates, sensitivity and specificity summaries, and recovered
HSROC parameters from the Rutter–Gatsonis parameterization.
## S3 method for class 'ReitsmaSubgroup' summary(object, ...)## S3 method for class 'ReitsmaSubgroup' summary(object, ...)
object |
An object of class |
... |
Additional arguments (currently ignored). |
A list of class "summary.ReitsmaSubgroup" with the following components:
estimates: Parameter estimates with standard errors.
sensspec: Estimated sensitivity and specificity with confidence intervals.
RutterGatsonis_recovered: Recovered parameters in the Rutter-Gatsonis (HSROC) parameterization.
subgroups Subgroup names.
Extracts key results from an object of class "ReitsmaSubgroupLCA", including
parameter estimates, sensitivity and specificity summaries, and recovered
HSROC parameters from the Rutter–Gatsonis parameterization.
## S3 method for class 'ReitsmaSubgroupLCA' summary(object, ...)## S3 method for class 'ReitsmaSubgroupLCA' summary(object, ...)
object |
An object of class |
... |
Additional arguments (currently ignored). |
A list of class "summary.ReitsmaSubgroupLCA" with the following components:
estimates: Parameter estimates with standard errors.
sensspec: Estimated sensitivity and specificity with confidence intervals.
prevref: Estimated (average) prevalence and reference standard sensitivity/specificity with confidence intervals.
RutterGatsonis_recovered: Recovered parameters in the Rutter-Gatsonis (HSROC) parameterization.
Extracts key results from an object of class "ReitsmaSubgroupTMB", including
parameter estimates, sensitivity and specificity summaries, and recovered
HSROC parameters from the Rutter–Gatsonis parameterization.
## S3 method for class 'ReitsmaSubgroupTMB' summary(object, ...)## S3 method for class 'ReitsmaSubgroupTMB' summary(object, ...)
object |
An object of class |
... |
Additional arguments (currently ignored). |
A list of class "summary.ReitsmaSubgroupTMB" with the following components:
estimates: Parameter estimates with standard errors.
sensspec: Estimated sensitivity and specificity with confidence intervals.
RutterGatsonis_recovered: Recovered parameters in the Rutter-Gatsonis (HSROC) parameterization.
subgroups Subgroup names.
Extracts key results from an object of class "ReitsmaTMB", including
parameter estimates, sensitivity and specificity summaries, and recovered
HSROC parameters from the Rutter–Gatsonis parameterization.
## S3 method for class 'ReitsmaTMB' summary(object, ...)## S3 method for class 'ReitsmaTMB' summary(object, ...)
object |
An object of class |
... |
Additional arguments (currently ignored). |
A list of class "summary.ReitsmaTMB" with the following components:
estimates: Parameter estimates with standard errors.
sensspec: Estimated sensitivity and specificity with confidence intervals.
RutterGatsonis_recovered: Recovered parameters in the Rutter-Gatsonis (HSROC) parameterization.
This method extracts key components from a fitted HSROC model object
returned by fitRutterGatsonis. It returns parameter
estimates, sensitivity/specificity summaries, and the recovered
Reitsma parameterization.
## S3 method for class 'RutterGatsonis' summary(object, ...)## S3 method for class 'RutterGatsonis' summary(object, ...)
object |
An object of class |
... |
Additional arguments (currently unused). |
Provides a concise summary of a fitted "RutterGatsonis" model.
A list of class "summary.RutterGatsonis" containing the following components:
estimates Parameter estimates with standard errors as returned from TMB reported parameters.
sensspec Estimated sensitivity at the specified
specificity, including confidence intervals.
Reitsma_recovered Recovered parameters in the Reitsma parameterization.
This method extracts key components from a fitted HSROC model object
returned by fitRutterGatsonisLCA. It returns parameter
estimates, sensitivity/specificity summaries, and the recovered
Reitsma parameterization.
## S3 method for class 'RutterGatsonisLCA' summary(object, ...)## S3 method for class 'RutterGatsonisLCA' summary(object, ...)
object |
An object of class |
... |
Additional arguments (currently unused). |
Provides a concise summary of a fitted "RutterGatsonisLCA" model.
A list of class "summary.RutterGatsonisLCA" containing the following components:
estimates: Parameter estimates with standard errors as returned from TMB reported parameters.
sensspec: Estimated index test sensitivity at the specified specificity, including confidence intervals.
prevref: Estimated (average) prevalence and reference standard sensitivity/specificity with confidence intervals.
Reitsma_recovered: Recovered parameters in the Reitsma parameterization.
This method extracts key components from a fitted HSROC model object
returned by fitRutterGatsonisReg. It returns parameter
estimates, sensitivity/specificity summaries.
## S3 method for class 'RutterGatsonisReg' summary(object, ...)## S3 method for class 'RutterGatsonisReg' summary(object, ...)
object |
An object of class |
... |
Additional arguments (currently unused). |
Provides a concise summary of a fitted "RutterGatsonisReg" model.
A list of class "summary.RutterGatsonisReg" containing the following components:
estimates Parameter estimates with standard errors as returned from TMB reported parameters.
sensspec Estimated sensitivity at the specified
specificity, including confidence intervals.
This method extracts key components from a fitted HSROC model object
returned by fitRutterGatsonisSubgroup. It returns parameter
estimates and sensitivity/specificity summaries.
## S3 method for class 'RutterGatsonisSubgroup' summary(object, ...)## S3 method for class 'RutterGatsonisSubgroup' summary(object, ...)
object |
An object of class |
... |
Additional arguments (currently unused). |
Provides a concise summary of a fitted "RutterGatsonisSubgroup" model.
A list of class "summary.RutterGatsonisSubgroup" containing the following components:
estimates Parameter estimates with standard errors as returned from TMB reported parameters.
sensspec Estimated sensitivity at the specified
specificity, including confidence intervals.
Reitsma_recovered Recovered parameters in the Reitsma parameterization.
subgroups Subgroup names.
Extracts key results from an object of class "RutterGatsonisSubgroupLCA", including
parameter estimates, sensitivity and specificity summaries, and recovered
HSROC parameters from the Rutter–Gatsonis parameterization.
## S3 method for class 'RutterGatsonisSubgroupLCA' summary(object, ...)## S3 method for class 'RutterGatsonisSubgroupLCA' summary(object, ...)
object |
An object of class |
... |
Additional arguments (currently ignored). |
A list of class "summary.RutterGatsonisSubgroupLCA" with the following components:
estimates: Parameter estimates with standard errors.
sensspec: Estimated index test sensitivity at the specified specificity, including confidence intervals.
prevref: Estimated (average) prevalence and reference standard sensitivity/specificity with confidence intervals.
Reitsma_recovered: Recovered parameters in the Reitsma parameterization.
This is the tub dataset from Kohli et al. (2018) from a meta-analysis examining the accuracy of the GeneXpert test for tuberculosis meningitis. In each study the index test was GeneXpert and the (imperfect) reference standard was culture.
tubtub
A data frame with 29 rows and 5 variables:
Study identifier
Number testing positive with both tests
Number testing positive with index test but negative with reference test
Number testing negative with index test but positive with reference test
Number testing negative with both tests
The dataset was taken from the supplementary material of the Cochrane Handbook for Systematic Reviews of Diagnostic Test Accuracy Studies.
Deeks, J. J., Bossuyt, P. M., Leeflang, M. M., & Takwoingi, Y. (editors) (2023). Cochrane Handbook for Systematic Reviews of Diagnostic Test Accuracy. Version 2.0 (updated July 2023). Cochrane.
Kohli, M. et al. (2018). Xpert MTB/RIF assay for extrapulmonary tuberculosis and rifampicin resistance. Cochrane Database of Systematic Reviews 2018, 8, CD012768. doi:10.1002/14651858.CD012768.pub2
Returns the variance-covariance matrix of the estimated model parameters.
## S3 method for class 'DTAmodel' vcov(object, ...) ## S3 method for class 'Reitsma' vcov(object, ...) ## S3 method for class 'ReitsmaSubgroup' vcov(object, ...) ## S3 method for class 'ReitsmaLCA' vcov(object, ...) ## S3 method for class 'ReitsmaSubgroupLCA' vcov(object, ...)## S3 method for class 'DTAmodel' vcov(object, ...) ## S3 method for class 'Reitsma' vcov(object, ...) ## S3 method for class 'ReitsmaSubgroup' vcov(object, ...) ## S3 method for class 'ReitsmaLCA' vcov(object, ...) ## S3 method for class 'ReitsmaSubgroupLCA' vcov(object, ...)
object |
A fitted model object. |
... |
Not currently used. |
A variance-covariance matrix corresponding to the parameters returned by
coef().
For ReitsmaSubgroup models, the returned
variance-covariance matrix corresponds to the cell-means
parameterization returned by coef().