Meta-analysis of proportions is conceptually simple: Faced with a binary outcome in multiple studies, we seek inference on some overall proportion of successes/failures. Under common effect models, exact inference has long been available, but is not when we more realistically allow for heterogeneity of the proportions. Instead a wide range of…

Effect sizes are important because they are an accessible way to indicate the practical importance of observed associations or differences. Standardized mean difference (SMD) effect sizes, such as Cohen's d, are widely used in education and the social sciences -- in part because they are relatively easy to calculate. However, SMD effect sizes…

Single case experimental designs are an important research design in behavioral and medical research. Although there are design standards prescribed by the What Works Clearinghouse for single case experimental designs, these standards do not include statistically derived power computations. Recently we derived the equations for computing power for…

A class of effect size indices are discussed that evaluate the degree to which two nested confirmatory factor analysis models differ from each other in terms of fit to a set of observed variables. These descriptive effect measures can be used to quantify the impact of parameter restrictions imposed in an initially considered model and are free…

Data collected from surveys can result in hundreds of variables and thousands of respondents. This implies that time and energy must be devoted to (a) carefully entering the data into a database, (b) running preliminary analyses to identify any problems (e.g., missing data, potential outliers), (c) checking the reliability and validity of the…

Methodologists have recently proposed robust variance estimation as one way to handle dependent effect sizes in meta-analysis. Software macros for robust variance estimation in meta-analysis are currently available for Stata (StataCorp LP, College Station, TX, USA) and SPSS (IBM, Armonk, NY, USA), yet there is little guidance for authors regarding…

When evaluators plan site-randomized experiments, they must conduct the appropriate statistical power analyses. These analyses are most likely to be valid when they are based on data from the jurisdictions in which the studies are to be conducted. In this method note, we provide software code, in the form of a SAS macro, for producing statistical…

This conference presentation demonstrates a multilevel model for analyzing single case designs. The model is implemented in the Bayesian program WinBUGS. The authors show how it is possible to estimate a d-statistic like the one in Hedges, Pustejovsky and Shadish (2012) in this program. Results are demonstrated on an example.

This toolkit, developed by Regional Educational Laboratory (REL) Central in collaboration with York Public Schools in Nebraska, provides a process and tools to help teachers use data from their classroom assessments to evaluate promising practices. The toolkit provides teachers with guidance on how to deliberately apply and study one classroom…

This article presents statistical power analysis (SPA) based on the normal distribution using Excel, adopting textbook and SPA approaches. The objective is to present the latter in a comparative way within a framework that is familiar to textbook level readers, as a first step to understand SPA with other distributions. The analysis focuses on the…

This note suggests delta method implementations for deriving confidence intervals for a latent mean effect size measure for the case of 2 independent populations. A hypothetical kindergarten reading example using these implementations is provided, as is supporting LISREL syntax. (Contains 1 table.)

Power computations for one-level experimental designs that assume simple random samples are greatly facilitated by power tables such as those presented in Cohen's book about statistical power analysis. However, in education and the social sciences experimental designs have naturally nested structures and multilevel models are needed to compute the…

Standard least squares analysis of variance methods suffer from poor power under arbitrarily small departures from normality and fail to control the probability of a Type I error when standard assumptions are violated. This article describes a framework for robust estimation and testing that uses trimmed means with an approximate degrees of…

This paper provides a brief review of the concepts of confidence intervals, effect sizes, and central and noncentral distributions. The use of confidence intervals around effect sizes is discussed. A demonstration of the Exploratory Software for Confidence Intervals (G. Cuming and S. Finch, 2001; ESCI) is given to illustrate effect size confidence…

This paper discusses how a seldom-used statistical procedure, recursive regression (RR), can numerically and graphically illustrate data-driven nonlinear relationships and interaction of variables. This routine falls into the family of exploratory techniques, yet a few interesting features make it a valuable compliment to factor analysis and…