USING RANDOM RATHER THAN FIXED EFFECTS MODELS IN METAANALYSIS - IMPLICATIONS FOR SITUATIONAL SPECIFICITY AND VALIDITY GENERALIZATION

Combining statistical information across studies (i.e., meta-analysis) is a standard research tool in applied psychology. The most common me ta-analytic approach in applied psychology, the fixed effects approach , assumes that individual studies are homogeneous and are sampled from the same population. This model assumes that sampling error alone exp lains the majority of observed differences in study effect sizes and i ts use has lead some to challenge the notion of situational specificit y in favor of validity generalization. We critique the fixed effects m ethodology and propose an advancement-the random effects model (RE) wh ich provides estimates of how between-study differences influence the relationships under study. RE models assume that studies are heterogen eous since they are often conducted by different investigators under d ifferent settings. Parameter estimates of both models are compared and evidence in favor of the random effects approach is presented. We arg ue against use of the fixed effects model because it may lead to misle ading conclusions about situational specificity.