When It’s OK to Use P-Values to Make Dichotomous Decisions
The never-ending criticism of p-values might make researchers doubt if the use of p-values is in any way defensible. Attempts to ban p-values, or to move beyond p < 0.05, suggest p-values are mainly harmful, and will lead to undesirable dichotomous statistical inferences. In this presentation I will discuss when p-values are a useful tool to answer a research question, and how dichotomous decisions were intended to be used in a methodological falsificationist framework. In experimental psychology p-values often answer a question of interest to researchers, and researchers should feel confident enough to use this statistical tool when appropriate. Furthermore, it is unlikely alternative statistical tools will fare any better in practice, and solutions to the misuse of statistics will require more rigorous solutions than changing the statistic we calculate.
Meeting ID: 989 9338 0810