Bayesian Inference on Risk Differences: An Application to Multivariate Meta-Analysis of Adverse Events in Clinical Trials

Yong Chen; Sheng Luo; Haitao Chu; Peng Wei

doi:10.1080/19466315.2013.791483

Bayesian Inference on Risk Differences: An Application to Multivariate Meta-Analysis of Adverse Events in Clinical Trials

Yong Chen, Sheng Luo, Haitao Chu, Peng Wei

Biostatistics

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

Multivariate meta-analysis is useful in combining evidence from independent studies that involve several comparisons among groups based on a single outcome. For binary outcomes, the commonly used statistical models for multivariate meta-analysis are multivariate generalized linear mixed effects models which assume risks, after some transformation, follow a multivariate normal distribution with possible correlations. In this article, we consider an alternative model for multivariate meta-analysis where the risks are modeled by the multivariate beta distribution proposed by Sarmanov. This model has several attractive features compared to the conventional multivariate generalized linear mixed effects models, including simplicity of likelihood function, no need to specify a link function, and a closed-form expression of distribution functions for study-specific risk differences. We investigate the finite sample performance of this model through simulation studies and illustrate its use with an application to multivariate meta-analysis of adverse events of tricyclic antidepressant treatment in clinical trials.

Original language	English (US)
Pages (from-to)	142-155
Number of pages	14
Journal	Statistics in Biopharmaceutical Research
Volume	5
Issue number	2
DOIs	https://doi.org/10.1080/19466315.2013.791483
State	Published - Apr 2013

Bibliographical note

Funding Information:
The authors are grateful to Dr. Steven Snapinn, the Associate Editor, and two anonymous reviewers for the helpful comments that have greatly improved this article. Yong Chen’s research was partially supported by a start-up fund and the PRIME award from the University of Texas School of Public Health. Sheng Luo’s research is partially supported by two NIH/NINDS grants U01NS043127 and U01NS43128. Haitao Chu was supported in part by the U.S. Department of Health and Human Services Agency for Healthcare Research and Quality grant R03HS020666, and P01CA142538 P30CA077598 from the U.S. National Cancer Institute. Peng Wei was supported in part by the National Institutes of Health grant HL095511.

Keywords

Bivariate beta-binomial model
Exact method
Hypergeometric function
Relative risk
Sarmanov family

Publisher link

10.1080/19466315.2013.791483

Find It

Find It at U of M Libraries

Cite this

@article{cae1081101e34b498df0276fe5d63cf9,

title = "Bayesian Inference on Risk Differences: An Application to Multivariate Meta-Analysis of Adverse Events in Clinical Trials",

abstract = "Multivariate meta-analysis is useful in combining evidence from independent studies that involve several comparisons among groups based on a single outcome. For binary outcomes, the commonly used statistical models for multivariate meta-analysis are multivariate generalized linear mixed effects models which assume risks, after some transformation, follow a multivariate normal distribution with possible correlations. In this article, we consider an alternative model for multivariate meta-analysis where the risks are modeled by the multivariate beta distribution proposed by Sarmanov. This model has several attractive features compared to the conventional multivariate generalized linear mixed effects models, including simplicity of likelihood function, no need to specify a link function, and a closed-form expression of distribution functions for study-specific risk differences. We investigate the finite sample performance of this model through simulation studies and illustrate its use with an application to multivariate meta-analysis of adverse events of tricyclic antidepressant treatment in clinical trials.",

keywords = "Bivariate beta-binomial model, Exact method, Hypergeometric function, Relative risk, Sarmanov family",

author = "Yong Chen and Sheng Luo and Haitao Chu and Peng Wei",

note = "Funding Information: The authors are grateful to Dr. Steven Snapinn, the Associate Editor, and two anonymous reviewers for the helpful comments that have greatly improved this article. Yong Chen{\textquoteright}s research was partially supported by a start-up fund and the PRIME award from the University of Texas School of Public Health. Sheng Luo{\textquoteright}s research is partially supported by two NIH/NINDS grants U01NS043127 and U01NS43128. Haitao Chu was supported in part by the U.S. Department of Health and Human Services Agency for Healthcare Research and Quality grant R03HS020666, and P01CA142538 P30CA077598 from the U.S. National Cancer Institute. Peng Wei was supported in part by the National Institutes of Health grant HL095511.",

year = "2013",

month = apr,

doi = "10.1080/19466315.2013.791483",

language = "English (US)",

volume = "5",

pages = "142--155",

journal = "Statistics in Biopharmaceutical Research",

issn = "1946-6315",

publisher = "Taylor and Francis Ltd.",

number = "2",

}

TY - JOUR

T1 - Bayesian Inference on Risk Differences

T2 - An Application to Multivariate Meta-Analysis of Adverse Events in Clinical Trials

AU - Chen, Yong

AU - Luo, Sheng

AU - Chu, Haitao

AU - Wei, Peng

N1 - Funding Information: The authors are grateful to Dr. Steven Snapinn, the Associate Editor, and two anonymous reviewers for the helpful comments that have greatly improved this article. Yong Chen’s research was partially supported by a start-up fund and the PRIME award from the University of Texas School of Public Health. Sheng Luo’s research is partially supported by two NIH/NINDS grants U01NS043127 and U01NS43128. Haitao Chu was supported in part by the U.S. Department of Health and Human Services Agency for Healthcare Research and Quality grant R03HS020666, and P01CA142538 P30CA077598 from the U.S. National Cancer Institute. Peng Wei was supported in part by the National Institutes of Health grant HL095511.

PY - 2013/4

Y1 - 2013/4

N2 - Multivariate meta-analysis is useful in combining evidence from independent studies that involve several comparisons among groups based on a single outcome. For binary outcomes, the commonly used statistical models for multivariate meta-analysis are multivariate generalized linear mixed effects models which assume risks, after some transformation, follow a multivariate normal distribution with possible correlations. In this article, we consider an alternative model for multivariate meta-analysis where the risks are modeled by the multivariate beta distribution proposed by Sarmanov. This model has several attractive features compared to the conventional multivariate generalized linear mixed effects models, including simplicity of likelihood function, no need to specify a link function, and a closed-form expression of distribution functions for study-specific risk differences. We investigate the finite sample performance of this model through simulation studies and illustrate its use with an application to multivariate meta-analysis of adverse events of tricyclic antidepressant treatment in clinical trials.

AB - Multivariate meta-analysis is useful in combining evidence from independent studies that involve several comparisons among groups based on a single outcome. For binary outcomes, the commonly used statistical models for multivariate meta-analysis are multivariate generalized linear mixed effects models which assume risks, after some transformation, follow a multivariate normal distribution with possible correlations. In this article, we consider an alternative model for multivariate meta-analysis where the risks are modeled by the multivariate beta distribution proposed by Sarmanov. This model has several attractive features compared to the conventional multivariate generalized linear mixed effects models, including simplicity of likelihood function, no need to specify a link function, and a closed-form expression of distribution functions for study-specific risk differences. We investigate the finite sample performance of this model through simulation studies and illustrate its use with an application to multivariate meta-analysis of adverse events of tricyclic antidepressant treatment in clinical trials.

KW - Bivariate beta-binomial model

KW - Exact method

KW - Hypergeometric function

KW - Relative risk

KW - Sarmanov family

UR - http://www.scopus.com/inward/record.url?scp=84880986848&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84880986848&partnerID=8YFLogxK

U2 - 10.1080/19466315.2013.791483

DO - 10.1080/19466315.2013.791483

M3 - Article

AN - SCOPUS:84880986848

SN - 1946-6315

VL - 5

SP - 142

EP - 155

JO - Statistics in Biopharmaceutical Research

JF - Statistics in Biopharmaceutical Research

IS - 2

ER -

Bayesian Inference on Risk Differences: An Application to Multivariate Meta-Analysis of Adverse Events in Clinical Trials

Abstract

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this