On 3 May at 12:00 in room 2628-303, there will be an OSA seminar by Jesper Wulff (ECON) entitled:

How and why alpha should depend on sample size: A Bayesian-frequentist compromise for significance testing
 

Abstract
In management research, fixed alpha levels in statistical testing are ubiquitous. However, in highly powered studies, they can lead to Lindley’s paradox; a situation where the null hypothesis is rejected despite evidence in the test actually supporting it. We propose a sample size-dependent alpha level that combines the benefits of both frequentist and Bayesian statistics, enabling strict hypothesis testing with known error rates while also quantifying the evidence for a hypothesis. We provide an R-package to implement our method for generalized linear models, including linear regression, logistic regression, and Poisson regression. By using this approach, researchers can avoid mindless defaults and instead justify alpha as a function of sample size, thus improving the reliability of statistical analysis in management research.

Link to article (preprint): https://psyarxiv.com/3cbh7/

Everyone is welcome!