Adaptive α Significance Level for Linear Models
share
We put forward an adaptive alpha that decreases as the information grows, for hypothesis tests in which nested linear models are compared. A less elaborate adaptation was already presented in <cit.> for comparing general i.i.d. models. In this article we present refined versions to compare nested linear models. This calibration may be interpreted as a Bayes-non-Bayes compromise, and leads to statistical consistency, and most importantly, it is a step forward towards statistics that leads to reproducible scientific findings.
READ FULL TEXT