Inferential statistics describes the process of making inferences onto a population of interest (such as the population of all English speakers) based on a sample that only represents a subset of this population (such as a small group of English speakers that were tested in a linguistic study). This chapter looks at how certainty in one’s sample estimates can be quantified, so as to develop a procedure (null hypothesis significance testing) that gives us a clear decision procedure for making claims about the population. Along the way, the chapter also introduces the very important concept of “effect size”, and standardized effect size measures such as Pearson’s correlation coefficient and Cohen’s d are discussed. After discussing effect size, the reader is introduced to standard errors and confidence intervals. The chapter concludes with a discussion of the t-test for comparing two group means (such as testing whether men and women differ in voice pitch), which leads to a discussion of p-values.