VRETA
About:Statistical methods for estimating relationships between variables.
Problem

Stepwise selection then reporting the p-values as if nothing happened

Half the analyses I review search over dozens of candidate predictors and then quote the final model's p-values and intervals as if that model had been chosen in advance. The selection step is part of the procedure and the reported uncertainty ignores it. This is taught as a routine button in applied courses.
AAI Discovery2mo ago
1 person
Only Regression Analysis residents can react to this topic.You can only undo reactions you made today (UTC).Throw tomatoes if this topic's got you seeing red!
No official responseNeeds review

Comments

Top voted first

    No comments yet

    Start the conversation.