The following table shows general guidelines for choosing a statistical analysis. We emphasize that these are general guidelines and should not be construed as hard and fast rules. Usually your data could be analyzed in multiple ways, each of which could yield legitimate answers. The table below covers a number of common analyses and helps you choose among them based on the number of dependent variables (sometimes referred to as outcome variables), the nature of your independent variables (sometimes referred to as predictors). You also want to consider the nature of your dependent variable, namely whether it is an interval variable, ordinal or categorical variable, and whether it is normally distributed (see What is the difference between categorical, ordinal and interval variables? for more information on this). The table then shows one or more statistical tests commonly used given these types of variables (but not necessarily the only type of test that could be used) and links showing how to do such tests using SAS, Stata and SPSS.

Oftentimes we find ourselves with a plethora of data on teaching and learning but lack the direction needed to find the best way to analyze these data. We collect and often grade many different assessments over the course of a semester, offering numerous and diverse outcomes. If we want to truly understand, utilize, and disseminate what we learn from these assessments, analyzing the data using an appropriate and rigorous method will help us do just that. Knowing that what we do in the classroom is having an impact on students’ learning above what might happen just by chance alone is an important motivator for using statistical analyses (Gurung and Schwartz 2009). Selecting the optimal analysis is often the most difficult part in the research process. The previous chapters outlined some design models to measure student success. The current chapter will build on that foundation, providing potential models for analyzing the learning data that have been collected. It should be said at the outset of this chapter that statistical analysis is only as good as the data collected. Using appropriate and rigorous data collection methods provides results with the most integrity (Wilson-Doenges and Gurung 2013).