The need for replication

Abstract

Replication provides verification and disconfirmation functions for the scholarly fields. Relatively few replications were found in a survey of studies in JSHD and JSHR over a recent decade. Based on the probabilities of Type I and Type II errors, there are likely to be approximately 50 to 250 false findings in this literature. Because many studies had relatively small sample sizes, replication would be helpful for extending the generalization of their results. These data underscore the urgency for more replications in the field.