Teaching Thoughtful Statistical Inference: Stories for the World Beyond p  < 0.05

Abstract

Statistical hypothesis tests and p values are poorly understood by many students of statistics. Poor application and misinterpretation of statistical inference procedures are common in published research. Over‐reliance on the “ p < 0.05” threshold to claim “statistical significance” often masks weaknesses in the evaluation of statistical evidence. This state of affairs presents a challenge for statistics education. This article proposes to teach statistical inference in the context of teaching statistical thinking. We need to introduce students to the different ways in which statistical inference is conducted in real research, demonstrate good practice, and show what can go wrong when p values are misinterpreted, misapplied, or intentionally gamed. Narratives from the history of statistics and science can aid in this endeavor. They provide context‐rich examples that show in specific yet generalizable ways the uses and pitfalls of hypothesis tests and other inferential procedures.