ABSTRACT
This unit explains the central logic of null hypothesis testing, including p-values, sampling distributions, one- and two-tailed tests, and other concepts. But it also describes the limitations of focusing on statistical significance and discusses effect sizes, problematic analytical practices, incorrect interpretations of significance, and other topics that help contextualize the merits and limitations of null hypothesis testing. The unit also covers the concept of estimation, including related subterms such as confidence level, confidence interval, and sampling and standard error.
