Power Analysis Using R: A Helpful Technique for Social Work Researchers

Power analysis is a critical technique for determining the number of subjects needed to identify the effect of an intervention. This presentation will provide users with an overview of when and how to perform power analyses using R, a free computer programming language, and how to report their findings. There are several reasons to utilize power analysis. The most common use of this technique is to determine the number of subjects needed to identify an effect of a given size. Power analysis can also be employed to determine statistical power given an effect size and the number of participants available. For instance, if a researcher knows that there are only 50 subjects available to study an intervention, conducting a power analysis would be helpful in deciding if the study was worth doing. Many grant funders require the inclusion of a power analysis in research proposals. Often, it is cost effective to use a smaller sample, if possible. Another reason for doing so is ethical; why should participants be subjected to a research protocol if it is not necessary? Finally, being able to estimate an effect size with actual data or from the literature indicates familiarity with the research focus and demonstrates your expertise in the field to grant funders. As a result of these concerns, there is a need to include power analysis in the research and social work research curriculum.

The purpose of this workshop is to teach effective techniques for utilizing power analysis. This workshop has three objectives. First, participants will understand when to use power analysis to inform their research. Second, participants will be able to use R to perform power analysis for several commonly implemented statistical techniques. Finally, participants will learn how to interpret and assess the results of their power analysis and how to report their findings depending on the report they are producing.

In this workshop, we will take a hands-on approach to meeting our objectives. We will begin the presentation with a discussion of how to install and get started with R, a free, open-source statistical programming language. We will introduce the conceptual framework for power analysis and how to calculate different types of effect sizes necessary for different research situations. Using R's pwr package, the presenters will then demonstrate how to calculate power for the t-test, one-way ANOVA, proportions, chi-square (X2), and correlations. We will include a number of examples and scenarios participants can use in their research. Finally, the authors will discuss how to best report the results of power analysis depending on the purpose of the report. The presenters will make available to attendees all of the datasets and scripts used during the symposium so that they can get started using R to calculate statistical power on their own once the conference has concluded.