1-truncated C-vine copula mixed models for network meta-analysis of multiple diagnostic tests

Aristidis K. Nikoloulopoulos

arxiv: 2605.18167 · v1 · pith:RRNQLCNXnew · submitted 2026-05-18 · 📊 stat.ME

1-truncated C-vine copula mixed models for network meta-analysis of multiple diagnostic tests

Aristidis K. Nikoloulopoulos This is my paper

Pith reviewed 2026-05-20 00:43 UTC · model grok-4.3

classification 📊 stat.ME

keywords copula mixed modelsnetwork meta-analysisdiagnostic testsvine copulaGLMMrandom effectstail dependence

0 comments

The pith

1-truncated C-vine copula mixed models generalize GLMMs to capture tail dependencies in diagnostic test meta-analysis.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper proposes 1-truncated C-vine copula mixed models as a flexible alternative to generalized linear mixed models for jointly analyzing data from multiple test comparison, randomized, and non-comparative study designs in network meta-analysis of diagnostic tests. These models allow arbitrary distributions for random effects while modeling tail dependencies and asymmetries between tests. A sympathetic reader would care because more accurate synthesis of evidence on test performance could support better clinical decisions about patient testing. The authors back the proposal with a simulation study and a re-analysis of data on tests for deep vein thrombosis.

Core claim

1-truncated C-vine copula mixed models generalize the GLMM framework by allowing for arbitrary univariate distributions of the random effects and capturing tail dependencies and asymmetries, and findings indicate that they can offer improvements over GLMMs for network meta-analysis of multiple diagnostic tests.

What carries the argument

The 1-truncated C-vine copula structure, which builds the joint distribution of random effects across study designs by linking univariate margins with a truncated vine copula to capture dependencies.

Load-bearing premise

The 1-truncated C-vine copula structure correctly captures the joint distribution of random effects across the three study designs without introducing bias in the meta-analytic inferences.

What would settle it

In the simulation study, if the 1-truncated C-vine copula models show no lower bias, no better coverage of confidence intervals, or no higher efficiency than GLMMs across replicated datasets with known true parameters, the claim of improvement would be refuted.

Figures

Figures reproduced from arXiv: 2605.18167 by Aristidis K. Nikoloulopoulos.

read the original abstract

As meta-analysis of multiple diagnostic tests impacts clinical decision making and patient health, there is growing interest in statistical models that synthesize evidence from studies comparing multiple diagnostic tests. To compare the accuracy of multiple diagnostic tests in a single study, three designs are commonly used: (i) the multiple test comparison design; (ii) the randomized design, and (iii) the non-comparative design. Generalized linear mixed models (GLMMs) are currently the recommended approach for jointly meta-analyzing data from all three designs, enabling simultaneous inference. In this context, 1-truncated C-vine copula mixed models are proposed as a flexible and powerful alternative. These models generalize the GLMM framework by allowing for arbitrary univariate distributions of the random effects and capturing tail dependencies and asymmetries. We demonstrate the utility of our methods with an extensive simulation study and by insightfully re-analysing a case study on the network meta-analysis of diagnostic tests for deep vein thrombosis. Findings indicate that 1-truncated C-vine copula mixed models can offer improvements over GLMMs, supporting their adoption for network meta-analysis of multiple diagnostic tests.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

The paper offers 1-truncated C-vine copula mixed models as a flexible step beyond GLMMs for diagnostic test network meta-analysis, but the truncation may leave higher-order random-effect dependencies unmodeled.

read the letter

The core advance here is replacing the usual normal random effects in GLMMs with a 1-truncated C-vine copula structure that lets the univariate margins be anything and picks up tail dependence and asymmetry across the three study designs. That is a genuine generalization, and the abstract shows they back it with simulations plus a re-analysis of the deep-vein-thrombosis data. Those two pieces of evidence are what give the claim any weight; without them the proposal would be just another copula variant. The simulations apparently show gains over GLMMs, which is the practical point for people doing these meta-analyses. The case-study re-analysis is the other concrete check, and it is useful to see whether the extra flexibility changes the conclusions on test accuracy. The main soft spot is exactly the one the stress-test flags. A 1-truncated vine sets all conditional copulas after the first tree to independence. If the logit-sensitivity and logit-specificity residuals for the multiple-test, randomized, and non-comparative designs still have non-trivial conditional association once you condition on one of them, the model is misspecified. That misspecification can bias the marginal accuracy estimates even if the univariate margins are correct. The abstract does not report any diagnostic for residual conditional dependence, so it is hard to know how much this matters in practice. For a methods paper this is a moderate rather than fatal gap, but it is the part that needs the most scrutiny in review. This is work for specialists in medical statistics who already run network meta-analyses of diagnostic tests and want more flexible random-effect modeling. A reader who is not already inside that literature will not get much out of it. The paper is coherent on its own terms, has reproducible elements in the simulations, and is worth sending to referees rather than desk-rejecting. I would send it out but would ask the authors to add checks on the conditional-independence assumption.

Referee Report

1 major / 2 minor

Summary. The manuscript proposes 1-truncated C-vine copula mixed models as a flexible alternative to GLMMs for jointly meta-analyzing data from multiple-test-comparison, randomized, and non-comparative designs in network meta-analysis of diagnostic tests. The models generalize the GLMM framework by permitting arbitrary univariate random-effect distributions and by using a 1-truncated C-vine copula to capture pairwise tail dependencies and asymmetries among the random effects; an extensive simulation study and a re-analysis of a deep-vein-thrombosis diagnostic-test case study are presented to demonstrate improvements over GLMMs.

Significance. If the modeling assumptions hold, the approach would supply a more flexible dependence structure than standard GLMMs while retaining the ability to synthesize evidence across heterogeneous study designs. This could improve the precision and robustness of pooled sensitivity and specificity estimates that inform clinical decisions. The simulation design and real-data re-analysis constitute concrete, falsifiable support for the claimed gains.

major comments (1)

[Model specification and simulation study sections] The central claim that the 1-truncated C-vine correctly represents the joint distribution of random effects across the three designs rests on the assumption that all conditional copulas beyond the first tree are independence copulas. No diagnostic check, likelihood-ratio test against a fuller vine, or sensitivity analysis to higher-order dependence is reported; if non-trivial conditional associations exist (e.g., between logit-sensitivity and logit-specificity residuals after conditioning on one design), the truncation induces misspecification that can bias marginal meta-analytic estimates even when univariate margins are flexible.

minor comments (2)

[Introduction and Section 2] Notation for the three study designs and the mapping of random effects to each design should be introduced earlier and used consistently in the equations.
[Simulation results] The simulation tables would benefit from explicit reporting of bias, coverage, and mean-squared error for the key accuracy parameters under each data-generating scenario.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their constructive and detailed comments on our manuscript. The feedback highlights an important modeling assumption that warrants further attention. We respond point-by-point below and will revise the manuscript accordingly to strengthen the presentation and validation of the proposed 1-truncated C-vine copula mixed models.

read point-by-point responses

Referee: [Model specification and simulation study sections] The central claim that the 1-truncated C-vine correctly represents the joint distribution of random effects across the three designs rests on the assumption that all conditional copulas beyond the first tree are independence copulas. No diagnostic check, likelihood-ratio test against a fuller vine, or sensitivity analysis to higher-order dependence is reported; if non-trivial conditional associations exist (e.g., between logit-sensitivity and logit-specificity residuals after conditioning on one design), the truncation induces misspecification that can bias marginal meta-analytic estimates even when univariate margins are flexible.

Authors: We agree that the truncation assumption requires explicit validation to support the central claim. The 1-truncated C-vine was selected for parsimony, as it directly models the primary pairwise dependencies and tail asymmetries among random effects from the three study designs (multiple-test comparison, randomized, and non-comparative) while keeping the number of parameters manageable for meta-analytic applications. In the simulation study, data were generated exactly under the 1-truncated structure, and the model recovered the marginal parameters with lower bias and better coverage than GLMMs. Nevertheless, we acknowledge that unmodeled higher-order conditional dependence could in principle affect results. In the revised manuscript, we will add a dedicated sensitivity analysis section that (i) fits a 2-truncated C-vine where computationally feasible on the real data example, (ii) reports likelihood-ratio comparisons against the 1-truncated version, and (iii) includes graphical diagnostics (e.g., conditional copula scatter plots) to assess residual dependence after the first tree. These additions will quantify the practical impact of the truncation assumption on the pooled sensitivity and specificity estimates. revision: yes

Circularity Check

0 steps flagged

Minor self-citation present but core modeling proposal remains independent

full rationale

The paper proposes 1-truncated C-vine copula mixed models as a generalization of GLMMs that permits arbitrary univariate random-effect distributions and captures tail dependencies via the vine structure. This modeling choice is supported by an extensive simulation study and re-analysis of a deep vein thrombosis diagnostic test case study rather than any claimed prediction that reduces to a fitted input by construction. Self-citations to prior copula work appear for background on the vine truncation but do not carry the load of the main claim, which stays externally verifiable through the reported empirical results. No self-definitional loops, fitted-input predictions, or uniqueness theorems imported from the same authors are evident in the derivation chain.

Axiom & Free-Parameter Ledger

1 free parameters · 1 axioms · 0 invented entities

The central claim depends on standard mixed-model assumptions extended by copula dependence structures; specific parameters for the vine truncation and pair-copula families are estimated from data but not enumerated in the abstract.

free parameters (1)

vine copula parameters
Parameters controlling the dependence structure in the 1-truncated C-vine that are fitted to the meta-analytic data.

axioms (1)

domain assumption Random effects can be linked via copulas while preserving arbitrary marginal distributions.
Invoked to generalize GLMMs as stated in the abstract.

pith-pipeline@v0.9.0 · 5731 in / 1272 out tokens · 46653 ms · 2026-05-20T00:43:36.049060+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

49 extracted references · 49 canonical work pages

[1]

Aas, K., Czado, C., Frigessi, A., and Bakken, H. (2009). Pair-copula constructions of multiple dependence. Insurance: M athematics & E conomics , 44:182--198

work page 2009
[2]

Barthel, N., Geerdens, C., Czado, C., and Janssen, P. (2019). Dependence modeling for recurrent event times subject to right-censoring with D -vine copulas. Biometrics , 75(2):439--451

work page 2019
[3]

and Cooke, R

Bedford, T. and Cooke, R. M. (2002). Vines - a new graphical model for dependent random variables. Annals of Statistics , 30:1031--1068

work page 2002
[4]

Beunckens, C., Molenberghs, G., and Kenward, M. G. (2005). Direct likelihood analysis versus simple forms of imputation for missing data in randomized clinical trials. Clinical Trials , 2(5):379--386

work page 2005
[5]

M., Minion, J., Brewer, T., and Pai, M

Chartrand, C., Leeflang, M. M., Minion, J., Brewer, T., and Pai, M. (2012). Accuracy of rapid influenza diagnostic tests: A meta-analysis. Annals of Internal Medicine , 156(7):500--511

work page 2012
[6]

L., Adam, M., and Bagos, P

Dimou, N. L., Adam, M., and Bagos, P. G. (2016). A multivariate method for meta-analysis and comparison of diagnostic tests. Statistics in Medicine , 35(20):3509--3523

work page 2016
[7]

Dissmann, J., Brechmann, E., Czado, C., and Kurowicka, D. (2013). Selecting and estimating regular vine copulae and application to financial returns. Computational Statistics & Data Analysis , 59:52--69

work page 2013
[8]

Erhardt, T. M. and Czado, C. (2018). Standardized drought indices: a novel univariate and multivariate approach. Journal of the Royal Statistical Society: Series C (Applied Statistics) , 67(3):643--664

work page 2018
[9]

M., Czado, C., and Schepsmeier, U

Erhardt, T. M., Czado, C., and Schepsmeier, U. (2015). R-vine models for spatial time series with an application to daily mean temperature. Biometrics , 71(2):323--332

work page 2015
[10]

E., Acar, E

Hoque, M. E., Acar, E. F., and Torabi, M. (2022). A time-heterogeneous D -vine copula model for unbalanced and unequally spaced longitudinal data. Biometrics , 79(2):734--746

work page 2022
[11]

and Kuss, O

Hoyer, A. and Kuss, O. (2018). Meta-analysis for the comparison of two diagnostic tests to a common gold standard: A generalized linear mixed model approach. Statistical Methods in Medical Research , 27(5):1410--1421

work page 2018
[12]

and Lindskog, F

Hult, H. and Lindskog, F. ( 2002 ). Multivariate extremes, aggregation and dependence in elliptical distributions . Advances in Applied Probability , 34 : 587--608

work page 2002
[13]

Jackson, D., Riley, R., and White, I. R. (2011). Multivariate meta-analysis: Potential and promise. Statistics in Medicine , 30(20):2481--2498

work page 2011
[14]

Jackson, D., White, I., and Riley, R. (2020). Multivariate meta-analysis. In Schmid, C. H., Stijnen, T., and White, I. R., editors, Handbook of Meta-Analysis . Chapman & Hall

work page 2020
[15]

and White, I

Jackson, D. and White, I. R. (2018). When should meta-analysis avoid making hidden normality assumptions? Biometrical Journal , 60(6):1040--1058

work page 2018
[16]

Joe, H. (1997). Multivariate M odels and D ependence C oncepts . Chapman & Hall, London

work page 1997
[17]

Joe, H. (2014). Dependence Modeling with Copulas . Chapman & Hall, London

work page 2014
[18]

Joe, H., Li, H., and Nikoloulopoulos, A. K. (2010). Tail dependence functions and vine copulas. Journal of Multivariate Analysis , 101:252--270

work page 2010
[19]

Kadhem, S. H. and Nikoloulopoulos, A. K. (2021). Factor copula models for mixed data. British Journal of Mathematical and Statistical Psychology , 74(3):365--403

work page 2021
[20]

Kang, J., Brant, R., and Ghali, W. A. (2013). Statistical methods for the meta-analysis of diagnostic tests must take into account the use of surrogate standards. Journal of Clinical Epidemiology , 66(5):566--574

work page 2013
[21]

and Joe, H

Krupskii, P. and Joe, H. (2013). Factor copula models for multivariate data. Journal of Multivariate Analysis , 120:85--101

work page 2013
[22]

S., and Chu, H

Lian, Q., Hodges, J. S., and Chu, H. (2019). A bayesian hierarchical summary receiver operating characteristic model for network meta-analysis of diagnostic tests. Journal of the American Statistical Association , 114(527):949--961

work page 2019
[23]

Little, R. J. A. and Rubin, D. B. (2002). Mixed Normal and Non-Normal Data with Missing Values, Ignoring the Missing-Data Mechanism , chapter 14, pages 292--311. John Wiley & Sons, Ltd

work page 2002
[24]

G., and Chen, Y

Ma, X., Lian, Q., Chu, H., Ibrahim, J. G., and Chen, Y. (2018). A Bayesian hierarchical model for network meta-analysis of multiple diagnostic tests . Biostatistics , 19(1):87--102

work page 2018
[25]

and Lesaffre, E

Menten, J. and Lesaffre, E. (2015). A general framework for comparative bayesian meta-analysis of diagnostic studies. BMC Medical Research Methodology , 15:70

work page 2015
[26]

Nash, J. (1990). Compact Numerical Methods for Computers: Linear Algebra and Function Minimisation . Hilger, New York. 2nd edition

work page 1990
[27]

Nikoloulopoulos, A. K. (2015). A mixed effect model for bivariate meta-analysis of diagnostic test accuracy studies using a copula representation of the random effects distribution. Statistics in Medicine , 34:3842--3865

work page 2015
[28]

Nikoloulopoulos, A. K. (2017). A vine copula mixed effect model for trivariate meta-analysis of diagnostic test accuracy studies accounting for disease prevalence. Statistical Methods in Medical Research , 26(5):2270--2286

work page 2017
[29]

Nikoloulopoulos, A. K. (2018a). Hybrid copula mixed models for combining case-control and cohort studies in meta-analysis of diagnostic tests. Statistical Methods in Medical Research , 27(8):2540--2553

work page
[30]

Nikoloulopoulos, A. K. (2018b). On composite likelihood in bivariate meta-analysis of diagnostic test accuracy studies. AStA Advances in Statistical Analysis , 102:211--227

work page
[31]

Nikoloulopoulos, A. K. (2019). A D -vine copula mixed model for joint meta-analysis and comparison of diagnostic tests. Statistical Methods in Medical Research , 28(10-11):3286--3300

work page 2019
[32]

Nikoloulopoulos, A. K. (2020a). An extended trivariate vine copula mixed model for meta-analysis of diagnostic studies in the presence of non-evaluable outcomes. The International Journal of Biostatistics , 16(2)

work page
[33]

Nikoloulopoulos, A. K. (2020b). A multinomial quadrivariate D -vine copula mixed model for meta-analysis of diagnostic studies in the presence of non-evaluable subjects. Statistical Methods in Medical Research , 29(10):2988--3005

work page
[34]

Nikoloulopoulos, A. K. (2022). An one-factor copula mixed model for joint meta-analysis of multiple diagnostic tests. Journal of the Royal Statistical Society: Series A (Statistics in Society) , 185(3):1398--1423

work page 2022
[35]

Nikoloulopoulos, A. K. (2024). Joint meta-analysis of two diagnostic tests accounting for within and between studies dependence. Statistical Methods in Medical Research , 33(10):1800--1817

work page 2024
[36]

Nikoloulopoulos, A. K. (2025a). CopulaREMADA : C opula mixed models for multivariate meta-analysis of diagnostic test accuracy studies . R Foundation for Statistical Computing, Vienna, Austria. R package version 1.7.5, DOI: 10.32614/CRAN.package.CopulaREMADA https://doi.org/10.32614/CRAN.package.CopulaREMADA

work page doi:10.32614/cran.package.copularemada
[37]

Nikoloulopoulos, A. K. (2025b). Vine copula mixed models for meta-analysis of diagnostic accuracy studies without a gold standard. Biometrics , 81(2):ujaf037

work page
[38]

Nikoloulopoulos, A. K. and Joe, H. (2015). Factor copula models for item response data. Psychometrika , 80:126--150

work page 2015
[39]

K., Joe, H., and Li, H

Nikoloulopoulos, A. K., Joe, H., and Li, H. (2012). Vine copulas with asymmetric tail dependence and applications to financial return data. Computational Statistics & Data Analysis , 56:3659--3673

work page 2012
[40]

N., Aerts, M., and Arbyn, M

Nyaga, V. N., Aerts, M., and Arbyn, M. (2018a). Anova model for network meta-analysis of diagnostic test accuracy data. Statistical Methods in Medical Research , 27(6):1766--1784

work page
[41]

N., Arbyn, M., and Aerts, M

Nyaga, V. N., Arbyn, M., and Aerts, M. (2018b). Beta-binomial analysis of variance model for network meta-analysis of diagnostic test accuracy data. Statistical Methods in Medical Research , 27(8):2554--2566

work page
[42]

M., Rue, H., and Held, L

Paul, M., Riebler, A., Bachmann, L. M., Rue, H., and Held, L. (2010). Bayesian bivariate meta-analysis of diagnostic test studies using integrated nested laplace approximations. Statistics in Medicine , 29(12):1325--1339

work page 2010
[43]

M., Dias, S., Ades, A

Phillippo, D. M., Dias, S., Ades, A. E., Belger, M., Brnabic, A., Schacht, A., Saure, D., Kadziola, Z., and Welton, N. J. (2020). Multilevel network meta-regression for population-adjusted treatment comparisons. Journal of the Royal Statistical Society: Series A (Statistics in Society) , 183(3):1189--1210

work page 2020
[44]

Stroud, A. H. and Secrest, D. (1966). Gaussian Quadrature Formulas . Prentice-Hall, Englewood Cliffs, NJ

work page 1966
[45]

Takwoingi, Y., Leeflang, M., and Deeks, J. (2013). Empirical evidence of the importance of comparative studies of diagnostic test accuracy. Annals of Internal Medicine , 158(7):544--554

work page 2013
[46]

A., Hoaglin, D

Trikalinos, T. A., Hoaglin, D. C., Small, K. M., Terrin, N., and Schmid, C. H. (2014). Methods for the joint meta-analysis of multiple tests. Research Synthesis Methods , 5(4):294--312

work page 2014
[47]

Vacek, P. M. (1985). The effect of conditional dependence on the evaluation of diagnostic tests. Biometrics , 41(4):959--968

work page 1985
[48]

Vandenberg, O., Martiny, D., Rochas, O., van Belkum, A., and Kozlakidis, Z. (2021). Considerations for diagnostic covid-19 tests. Nature Reviews Microbiology , 19(3):171--183

work page 2021
[49]

Venta, E. R. and Venta, L. A. (1987). The diagnosis of deep-vein thrombosis: An application of decision analysis. Journal of the Operational Research Society , 38(7):615--624

work page 1987

[1] [1]

Aas, K., Czado, C., Frigessi, A., and Bakken, H. (2009). Pair-copula constructions of multiple dependence. Insurance: M athematics & E conomics , 44:182--198

work page 2009

[2] [2]

Barthel, N., Geerdens, C., Czado, C., and Janssen, P. (2019). Dependence modeling for recurrent event times subject to right-censoring with D -vine copulas. Biometrics , 75(2):439--451

work page 2019

[3] [3]

and Cooke, R

Bedford, T. and Cooke, R. M. (2002). Vines - a new graphical model for dependent random variables. Annals of Statistics , 30:1031--1068

work page 2002

[4] [4]

Beunckens, C., Molenberghs, G., and Kenward, M. G. (2005). Direct likelihood analysis versus simple forms of imputation for missing data in randomized clinical trials. Clinical Trials , 2(5):379--386

work page 2005

[5] [5]

M., Minion, J., Brewer, T., and Pai, M

Chartrand, C., Leeflang, M. M., Minion, J., Brewer, T., and Pai, M. (2012). Accuracy of rapid influenza diagnostic tests: A meta-analysis. Annals of Internal Medicine , 156(7):500--511

work page 2012

[6] [6]

L., Adam, M., and Bagos, P

Dimou, N. L., Adam, M., and Bagos, P. G. (2016). A multivariate method for meta-analysis and comparison of diagnostic tests. Statistics in Medicine , 35(20):3509--3523

work page 2016

[7] [7]

Dissmann, J., Brechmann, E., Czado, C., and Kurowicka, D. (2013). Selecting and estimating regular vine copulae and application to financial returns. Computational Statistics & Data Analysis , 59:52--69

work page 2013

[8] [8]

Erhardt, T. M. and Czado, C. (2018). Standardized drought indices: a novel univariate and multivariate approach. Journal of the Royal Statistical Society: Series C (Applied Statistics) , 67(3):643--664

work page 2018

[9] [9]

M., Czado, C., and Schepsmeier, U

Erhardt, T. M., Czado, C., and Schepsmeier, U. (2015). R-vine models for spatial time series with an application to daily mean temperature. Biometrics , 71(2):323--332

work page 2015

[10] [10]

E., Acar, E

Hoque, M. E., Acar, E. F., and Torabi, M. (2022). A time-heterogeneous D -vine copula model for unbalanced and unequally spaced longitudinal data. Biometrics , 79(2):734--746

work page 2022

[11] [11]

and Kuss, O

Hoyer, A. and Kuss, O. (2018). Meta-analysis for the comparison of two diagnostic tests to a common gold standard: A generalized linear mixed model approach. Statistical Methods in Medical Research , 27(5):1410--1421

work page 2018

[12] [12]

and Lindskog, F

Hult, H. and Lindskog, F. ( 2002 ). Multivariate extremes, aggregation and dependence in elliptical distributions . Advances in Applied Probability , 34 : 587--608

work page 2002

[13] [13]

Jackson, D., Riley, R., and White, I. R. (2011). Multivariate meta-analysis: Potential and promise. Statistics in Medicine , 30(20):2481--2498

work page 2011

[14] [14]

Jackson, D., White, I., and Riley, R. (2020). Multivariate meta-analysis. In Schmid, C. H., Stijnen, T., and White, I. R., editors, Handbook of Meta-Analysis . Chapman & Hall

work page 2020

[15] [15]

and White, I

Jackson, D. and White, I. R. (2018). When should meta-analysis avoid making hidden normality assumptions? Biometrical Journal , 60(6):1040--1058

work page 2018

[16] [16]

Joe, H. (1997). Multivariate M odels and D ependence C oncepts . Chapman & Hall, London

work page 1997

[17] [17]

Joe, H. (2014). Dependence Modeling with Copulas . Chapman & Hall, London

work page 2014

[18] [18]

Joe, H., Li, H., and Nikoloulopoulos, A. K. (2010). Tail dependence functions and vine copulas. Journal of Multivariate Analysis , 101:252--270

work page 2010

[19] [19]

Kadhem, S. H. and Nikoloulopoulos, A. K. (2021). Factor copula models for mixed data. British Journal of Mathematical and Statistical Psychology , 74(3):365--403

work page 2021

[20] [20]

Kang, J., Brant, R., and Ghali, W. A. (2013). Statistical methods for the meta-analysis of diagnostic tests must take into account the use of surrogate standards. Journal of Clinical Epidemiology , 66(5):566--574

work page 2013

[21] [21]

and Joe, H

Krupskii, P. and Joe, H. (2013). Factor copula models for multivariate data. Journal of Multivariate Analysis , 120:85--101

work page 2013

[22] [22]

S., and Chu, H

Lian, Q., Hodges, J. S., and Chu, H. (2019). A bayesian hierarchical summary receiver operating characteristic model for network meta-analysis of diagnostic tests. Journal of the American Statistical Association , 114(527):949--961

work page 2019

[23] [23]

Little, R. J. A. and Rubin, D. B. (2002). Mixed Normal and Non-Normal Data with Missing Values, Ignoring the Missing-Data Mechanism , chapter 14, pages 292--311. John Wiley & Sons, Ltd

work page 2002

[24] [24]

G., and Chen, Y

Ma, X., Lian, Q., Chu, H., Ibrahim, J. G., and Chen, Y. (2018). A Bayesian hierarchical model for network meta-analysis of multiple diagnostic tests . Biostatistics , 19(1):87--102

work page 2018

[25] [25]

and Lesaffre, E

Menten, J. and Lesaffre, E. (2015). A general framework for comparative bayesian meta-analysis of diagnostic studies. BMC Medical Research Methodology , 15:70

work page 2015

[26] [26]

Nash, J. (1990). Compact Numerical Methods for Computers: Linear Algebra and Function Minimisation . Hilger, New York. 2nd edition

work page 1990

[27] [27]

Nikoloulopoulos, A. K. (2015). A mixed effect model for bivariate meta-analysis of diagnostic test accuracy studies using a copula representation of the random effects distribution. Statistics in Medicine , 34:3842--3865

work page 2015

[28] [28]

Nikoloulopoulos, A. K. (2017). A vine copula mixed effect model for trivariate meta-analysis of diagnostic test accuracy studies accounting for disease prevalence. Statistical Methods in Medical Research , 26(5):2270--2286

work page 2017

[29] [29]

Nikoloulopoulos, A. K. (2018a). Hybrid copula mixed models for combining case-control and cohort studies in meta-analysis of diagnostic tests. Statistical Methods in Medical Research , 27(8):2540--2553

work page

[30] [30]

Nikoloulopoulos, A. K. (2018b). On composite likelihood in bivariate meta-analysis of diagnostic test accuracy studies. AStA Advances in Statistical Analysis , 102:211--227

work page

[31] [31]

Nikoloulopoulos, A. K. (2019). A D -vine copula mixed model for joint meta-analysis and comparison of diagnostic tests. Statistical Methods in Medical Research , 28(10-11):3286--3300

work page 2019

[32] [32]

Nikoloulopoulos, A. K. (2020a). An extended trivariate vine copula mixed model for meta-analysis of diagnostic studies in the presence of non-evaluable outcomes. The International Journal of Biostatistics , 16(2)

work page

[33] [33]

Nikoloulopoulos, A. K. (2020b). A multinomial quadrivariate D -vine copula mixed model for meta-analysis of diagnostic studies in the presence of non-evaluable subjects. Statistical Methods in Medical Research , 29(10):2988--3005

work page

[34] [34]

Nikoloulopoulos, A. K. (2022). An one-factor copula mixed model for joint meta-analysis of multiple diagnostic tests. Journal of the Royal Statistical Society: Series A (Statistics in Society) , 185(3):1398--1423

work page 2022

[35] [35]

Nikoloulopoulos, A. K. (2024). Joint meta-analysis of two diagnostic tests accounting for within and between studies dependence. Statistical Methods in Medical Research , 33(10):1800--1817

work page 2024

[36] [36]

Nikoloulopoulos, A. K. (2025a). CopulaREMADA : C opula mixed models for multivariate meta-analysis of diagnostic test accuracy studies . R Foundation for Statistical Computing, Vienna, Austria. R package version 1.7.5, DOI: 10.32614/CRAN.package.CopulaREMADA https://doi.org/10.32614/CRAN.package.CopulaREMADA

work page doi:10.32614/cran.package.copularemada

[37] [37]

Nikoloulopoulos, A. K. (2025b). Vine copula mixed models for meta-analysis of diagnostic accuracy studies without a gold standard. Biometrics , 81(2):ujaf037

work page

[38] [38]

Nikoloulopoulos, A. K. and Joe, H. (2015). Factor copula models for item response data. Psychometrika , 80:126--150

work page 2015

[39] [39]

K., Joe, H., and Li, H

Nikoloulopoulos, A. K., Joe, H., and Li, H. (2012). Vine copulas with asymmetric tail dependence and applications to financial return data. Computational Statistics & Data Analysis , 56:3659--3673

work page 2012

[40] [40]

N., Aerts, M., and Arbyn, M

Nyaga, V. N., Aerts, M., and Arbyn, M. (2018a). Anova model for network meta-analysis of diagnostic test accuracy data. Statistical Methods in Medical Research , 27(6):1766--1784

work page

[41] [41]

N., Arbyn, M., and Aerts, M

Nyaga, V. N., Arbyn, M., and Aerts, M. (2018b). Beta-binomial analysis of variance model for network meta-analysis of diagnostic test accuracy data. Statistical Methods in Medical Research , 27(8):2554--2566

work page

[42] [42]

M., Rue, H., and Held, L

Paul, M., Riebler, A., Bachmann, L. M., Rue, H., and Held, L. (2010). Bayesian bivariate meta-analysis of diagnostic test studies using integrated nested laplace approximations. Statistics in Medicine , 29(12):1325--1339

work page 2010

[43] [43]

M., Dias, S., Ades, A

Phillippo, D. M., Dias, S., Ades, A. E., Belger, M., Brnabic, A., Schacht, A., Saure, D., Kadziola, Z., and Welton, N. J. (2020). Multilevel network meta-regression for population-adjusted treatment comparisons. Journal of the Royal Statistical Society: Series A (Statistics in Society) , 183(3):1189--1210

work page 2020

[44] [44]

Stroud, A. H. and Secrest, D. (1966). Gaussian Quadrature Formulas . Prentice-Hall, Englewood Cliffs, NJ

work page 1966

[45] [45]

Takwoingi, Y., Leeflang, M., and Deeks, J. (2013). Empirical evidence of the importance of comparative studies of diagnostic test accuracy. Annals of Internal Medicine , 158(7):544--554

work page 2013

[46] [46]

A., Hoaglin, D

Trikalinos, T. A., Hoaglin, D. C., Small, K. M., Terrin, N., and Schmid, C. H. (2014). Methods for the joint meta-analysis of multiple tests. Research Synthesis Methods , 5(4):294--312

work page 2014

[47] [47]

Vacek, P. M. (1985). The effect of conditional dependence on the evaluation of diagnostic tests. Biometrics , 41(4):959--968

work page 1985

[48] [48]

Vandenberg, O., Martiny, D., Rochas, O., van Belkum, A., and Kozlakidis, Z. (2021). Considerations for diagnostic covid-19 tests. Nature Reviews Microbiology , 19(3):171--183

work page 2021

[49] [49]

Venta, E. R. and Venta, L. A. (1987). The diagnosis of deep-vein thrombosis: An application of decision analysis. Journal of the Operational Research Society , 38(7):615--624

work page 1987