Before embarking on an individual participant data meta-analysis (IPDMA) project, researchers should consider the power of their planned IPDMA conditional on the studies promising their IPD and their characteristics. Such power estimates help inform whether the IPDMA project is worth the time and funding investment, before IPD are collected. Here,…

The conventional Q statistic, using estimated inverse-variance (IV) weights, underlies a variety of problems in random-effects meta-analysis. In previous work on standardized mean difference and log-odds-ratio, we found superior performance with an estimator of the overall effect whose weights use only group-level sample sizes. The Q statistic…

The meta-analytic method proposed by S. W. Raudenbush (1988) for studying variance heterogeneity was studied. Results of a Monte Carlo study indicate that the Type I error rate of the test is sensitive to even modestly platykurtic score distributions and to the ratio of study sample size to the number of studies. (SLD)

The random variable p and its functions figure in several "tests of combined significance," meta-analysis summaries based on sample significance values, and ps have been used singly, as well as in other tests for evaluating the outcomes of individual research studies. In this work, asymptotic distributions of the sample one-sided…

The test of homogeneity developed by L. V. Hedges (1982) for the fixed effects model is frequently used in quantitative meta-analyses to test whether effect sizes are equal. Despite its widespread use, evidence of the behavior of this test for the less-than-ideal case of small study sample sizes paired with large numbers of studies is…

The use of p-values in combining results of studies often involves studies that are potentially aberrant. This paper proposes a combined test that permits trimming some of the extreme p-values. The trimmed statistic is based on an inverse cumulative normal transformation of the ordered p-values. (SLD)

The observed probability "p" is the social scientist's primary tool for evaluating the outcome of statistical hypothesis tests. The small-sample accuracy of nonnull asymptotic distributions of several functions of "p" was studied. Implications for use of the approximations are discussed. (SLD)

This paper is concerned with the construction of effect size standard errors in situations where the effect sizes are independent but the data have likely been sampled from non-normal distributions, and possibly for different studies, from different families of non-normal distributions. Asymptotic distribution-free estimators are provided for two…