This paper introduces a simple, quotient effect size, termed (for 'quotient'), suitable for reporting on the effectiveness of educational interventions. The quotient effect size for a pre-test-post-test design is defined as the gain score (i.e. post-test minus pre-test) for the intervention group, divided by the gain score for the control group.…

It is a healthy exercise to debate the merits of using effect-size benchmarks to interpret research findings. However, these debates obscure a more central insight that emerges from empirical distributions of effect-size estimates in the literature: Efforts to improve education often fail to move the needle. I find that 36% of effect sizes from…

Researchers often include covariates when they analyze the results of randomized controlled trials (RCTs), valuing the increased precision of the estimates over the potential of inducing small-sample bias when doing so. In this paper, we develop a sufficient condition which ensures that the inclusion of covariates does not induce small-sample bias…

A recent paper uses Bayes factors to argue a large minority of rigorous, large-scale education RCTs are "uninformative." The definition of "uninformative" depends on the authors' hypothesis choices for calculating Bayes factors. These arguably overadjust for effect size inflation and involve a fixed prior distribution,…

Ainsworth et al.'s paper "Sources of Bias in Outcome Assessment in Randomised Controlled Trials: A Case Study" examines alternative accounts for a large difference in effect size between 2 outcomes in the same intervention evaluation. It argues that the probable explanation relates to masking: Only one outcome measure was administered by…

The symptoms of autism spectrum disorder are conceptualized to alter the quality of parent--children interactions, exposure to social learning exchanges, and ultimately the course of child development. There is evidence that modifying the procedures of Pivotal Response Treatment (PRT) to explicitly target social motivation enhances child…

Field experiments in education frequently assign entire groups such as schools to treatment or control conditions. These experiments incorporate sometimes a longitudinal component where for example students are followed over time to assess differences in the average rate of linear change, or rate of acceleration. In this study, we provide methods…

Fricke et al. and Hagen et al. (2017) each report on large-scale pragmatic randomised controlled trials delivered in schools or nurseries, investigating language interventions for vulnerable children and showing moderate positive effect sizes. Such research is part of a recent development of 'what works' research in England, and the number of…

Most evaluators have embraced the goal of evidence-based practice (EBP). Yet, many have criticized EBP review systems that prioritize randomized control trials and use various criteria to limit the studies examined. They suggest this could produce policy recommendations based on small, unrepresentative segments of the literature and recommend a…

When cluster randomized experiments are analyzed as if units were independent, test statistics for treatment effects can be anticonservative. Hedges proposed a correction for such tests by scaling them to control their Type I error rate. This article generalizes the Hedges correction from a posttest-only experimental design to more common designs…

Experimental evaluations that involve the educational system usually involve a hierarchical structure (students are nested within classrooms that are nested within schools, etc.). Concerns about contamination, where research subjects receive certain features of an intervention intended for subjects in a different experimental group, have often led…