Meta‐analysis of a continuous outcome combining individual patient data and aggregate data: a method based on simulated individual patient data

Yamaguchi, Yusuke; Sakamoto, Wataru; Goto, Masashi; Staessen, Jan A.; Wang, Ji‐Guang; Gueyffier, François; Riley, Richard D

doi:10.1002/jrsm.1119

Cited by 5 publications

(2 citation statements)

References 55 publications

(96 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An extensive efficacy analysis of the one‐stage and two‐stage statistical methods for combining IPD and AD in meta‐analysis for continuous outcome was explored by Riley et al, 27‐30 among others. In the simple situation of a fixed effects model with a single continuous outcome and covariate, Yamaguchi et al 31 proposed a method to reconstruct the missing IPD for AD trials by a Bayesian sampling procedure and using the mixture of simulated IPD and collected IPD for an IPD meta‐analysis. Over the past decade, meta‐analysis methods for mixture data have also been developed for dichotomous outcomes and time‐to‐event data, some based on reconstruction of IPD 29,32,33 .…”

Section: Introductionmentioning

confidence: 99%

Efficient integration of aggregate data and individual participant data in one‐way mixed models

Agarwala

Park

2022

Statistics in Medicine

View full text Add to dashboard Cite

Often both aggregate data (AD) studies and individual participant data (IPD) studies are available for specific treatments. Combining these two sources of data could improve the overall meta‐analytic estimates of treatment effects. Moreover, often for some studies with AD, the associated IPD maybe available, albeit at some extra effort or cost to the analyst. We propose a method for combining treatment effects across trials when the response is from the exponential family of distribution and hence a generalized linear model structure can be used. We consider the case when treatment effects are fixed and common across studies. Using the proposed combination method, we study the relative efficiency of analyzing all IPD studies vs combining various percentages of AD and IPD studies. For many different models, design constraints under which the AD estimators are the IPD estimators, and hence fully efficient, are known. For such models, we advocate a selection procedure that chooses AD studies over IPD studies in a manner that force least departure from design constraints and hence ensures an efficient combined AD and IPD estimator.

show abstract

Section: Introductionmentioning

confidence: 99%

Efficient integration of aggregate data and individual participant data in one‐way mixed models

Agarwala

Park

2022

Statistics in Medicine

View full text Add to dashboard Cite

show abstract

“…An extensive efficacy analysis of the one-stage and two-stage statistical methods for combining IPD and AD in meta-analysis for continuous outcome was explored by Riley et al among others [26], [27], [28], [12]. In the simple situation of a fixed effects model with a single continuous outcome and covariate, Yamaguchi et al [41] proposed a method to reconstruct the missing IPD for AD trials by a Bayesian sampling procedure and use the mixture of simulated IPD and collected IPD for an IPD meta-analysis. Over the past decade, meta-analysis methods for mixture data have also been developed for dichotomous outcomes and time-to-event data, some based on reconstruction of IPD [9], [29], [28].…”

Section: Introductionmentioning

confidence: 99%

Efficient Integration of Aggregate Data and Individual Patient Data in One-Way Mixed Models

Agarwala¹,

Park²

2021

Preprint

View full text Add to dashboard Cite

Often both Aggregate Data (AD) studies and Individual Patient Data (IPD) studies are available for specific treatments. Combining these two sources of data could improve the overall meta-analytic estimates of treatment effects. Moreover, often for some studies with AD, the associated IPD maybe available, albeit at some extra effort or cost to the analyst. We propose a method for combining treatment effects across trials when the response is from the exponential family of distribution and hence a generalized linear model structure can be used. We consider the case when treatment effects are fixed and common across studies. Using the proposed combination method, we evaluate the wisdom of choosing AD when IPD is available by studying the relative efficiency of analyzing all IPD studies versus combining various percentages of AD and IPD studies. For many different models design constraints under which the AD estimators are the IPD estimators, and hence fully efficient, are known. For such models we advocate a selection procedure that chooses AD studies over IPD studies in a manner that force least departure from design constraints and hence ensures a fully efficient combined AD and IPD estimator.

show abstract

Integrative Data Analysis for Research in Developmental Psychopathology

Mun

Jiao

Xie

2016

Developmental Psychopathology

View full text Add to dashboard Cite

Researchers from many disciplines have increasingly called for changes in research practices to be more transparent and rigorous. One of the changes prominently discussed is the utilization of quantitative research synthesis from multiple single studies, which we broadly refer to as integrative data analysis (IDA). The present chapter discusses how IDA can be particularly helpful for research in developmental psychopathology. We provide a broad overview of evidence‐based quantitative approaches, covering different types of data, different analytical models, and complex research synthesis methods. We highlight the promise of utilizing individual participant‐level data from multiple single studies or networks of single studies for analyzing multiple related parameters (or multiple end points) within the framework of quantitative research synthesis. We provide several data examples to illustrate some of these methods. Through the use of innovative strategies for IDA, we can strengthen our research practices and expand our knowledge base cumulatively.

show abstract

Meta‐analysis of a continuous outcome combining individual patient data and aggregate data: a method based on simulated individual patient data

Cited by 5 publications

References 55 publications

Efficient integration of aggregate data and individual participant data in one‐way mixed models

Efficient integration of aggregate data and individual participant data in one‐way mixed models

Efficient Integration of Aggregate Data and Individual Patient Data in One-Way Mixed Models

Integrative Data Analysis for Research in Developmental Psychopathology

Contact Info

Product

Resources

About