Some Right Ways to Analyze (Psycho)Linguistic Data

Much has been written on the abuse and misuse of statistical methods, including p values, significance, so forth. I present some best practices in statistics using a running example data analysis. Focusing primarily frequentist Bayesian linear mixed models, illustrate defensible ways which inference—specifically, hypothesis testing Bayes factors versus estimation or uncertainty quantification—can be carried out. The key is to not overstate evidence expect too much from statistics. Along way, demonstrate powerful ideas, use simulation understand design properties one's experiment before it, visualization carrying out formal analysis, fitted model model's behavior.