B1700
Title: An introduction to second-generation p-values
Authors: Jeffrey Blume - University of Virginia (United States) [presenting]
Abstract: Despite decades of controversy, $p$-values remain a popular tool for assessing when the data are incompatible with the null hypothesis. While it is widely recognized that $p$-values are imperfect, the consequences of ignoring their flaws remain elusive and $p$-values continue to flourish in the scientific literature. We will introduce the second-generation $p$-value, a novel and intuitive extension that better serves the intended purpose. We will illustrate their use in several examples, including a high-dimensional genomics setting, and show how their implicit emphasis on scientific relevance leads to improved statistical performance (as measured by error rates or false discovery rates).