TY - UNPB
T1 - Correcting for publication bias in a meta-analysis with the P-uniform* method
AU - van Aert, Robbie
AU - van Assen, Marcel
PY - 2018
Y1 - 2018
N2 - Publication bias is a major threat to the validity of a meta-analysis resulting in overestimated effect sizes. We propose an extension and improvement of the publication bias method p-uniform called p-uniform*. P-uniform* improves upon p-uniform in three ways, as it (i) entails a more efficient estimator, (ii) eliminates the overestimation of effect size caused by between-study variance in true effect size, and (iii) enables estimating and testing for the presence of the between-study variance. We compared the statistical properties of p-uniform* with p-uniform, the selection model approach of Hedges (1992), and the random-effects model. Statistical properties of p-uniform* and the selection model approach were comparable and generally outperformed p-uniform and the random-effects model if publication bias was present. We demonstrate that p-uniform* and the selection model approach estimate average effect size and between-study variance rather well with ten or more studies in the meta-analysis when publication bias is not extreme. P-uniform* generally provides more accurate estimates of the between-study variance in meta-analyses containing many studies (e.g., 60 or more) and if publication bias is present. We offer recommendations for applied researchers, provide an R package as well as an easy-to-use web application for applying p-uniform*.
AB - Publication bias is a major threat to the validity of a meta-analysis resulting in overestimated effect sizes. We propose an extension and improvement of the publication bias method p-uniform called p-uniform*. P-uniform* improves upon p-uniform in three ways, as it (i) entails a more efficient estimator, (ii) eliminates the overestimation of effect size caused by between-study variance in true effect size, and (iii) enables estimating and testing for the presence of the between-study variance. We compared the statistical properties of p-uniform* with p-uniform, the selection model approach of Hedges (1992), and the random-effects model. Statistical properties of p-uniform* and the selection model approach were comparable and generally outperformed p-uniform and the random-effects model if publication bias was present. We demonstrate that p-uniform* and the selection model approach estimate average effect size and between-study variance rather well with ten or more studies in the meta-analysis when publication bias is not extreme. P-uniform* generally provides more accurate estimates of the between-study variance in meta-analyses containing many studies (e.g., 60 or more) and if publication bias is present. We offer recommendations for applied researchers, provide an R package as well as an easy-to-use web application for applying p-uniform*.
UR - https://osf.io/preprints/metaarxiv/zqjr9/
U2 - 10.31222/osf.io/zqjr9
DO - 10.31222/osf.io/zqjr9
M3 - Working paper
BT - Correcting for publication bias in a meta-analysis with the P-uniform* method
PB - MetaArXiv Preprints
ER -