Calculating and Synthesizing Effect Sizes

Abstract

The effect size is a standardized, scale-free measure of the relative size of the effect of an interven- tion, and it has important and practical implications for clinicians in the speech and hearing field who are interested in estimating the effects of interventions. This article develops a conceptual interpretation of the effect size, makes explicit assumptions for its proper use in estimating the size of the effect of behavioral-based stuttering interventions, and explains how to compute the most commonly used effect sizes and their confidence intervals. The focus is on effect sizes for experimental studies on behavioral-based stuttering interventions that produce outcomes measured on a continuous scale. Also explained is how to synthesize these effect sizes across multiple studies to arrive at an average effect size and its confidence interval through a process called meta- analysis. Key assumptions that underlie the use of meta- analysis are explored, as are techniques for assessing whether the average effect size is representative of the multiple effect sizes from which it was derived. The article concludes with a summary of main points and enumerates additional resources for speech and hearing clinicians and practitioners to access and learn more about practical applications of effect sizes and their synthesis through meta-analysis.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 219 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.