Behavior analysis has a strong tradition of establishing intervention effects in individual experimental subjects or participants instead of establishing the mean effect of an intervention in a group. This is often the best approach when assessing whether a treatment was successful for an individual subject in an applied setting. However, this approach can make it difficult to compare treatment approaches to one another or establish which treatment features are likely to provide the most benefit when implemented in a large number of patients. In this presentation, I will not delve into the details of specific statistical tests or the specifics on conducting them. Instead, I will make the case that inferential statistics can provide valuable information for behavior analysts in many situations. I will cover the types of experimental questions that are best addressed with an inferential statistical test and the benefits of calculating standardized effect sizes. Attendees should be able to identify experiments that would benefit from the addition of inferential statistics, describe the features of a experimental design that maximize the interpretive value of inferential statistics, and discriminate between appropriate and inappropriate conclusions that can be drawn from inferential statistical results.