Harrell’s primary mission is to combat . He argues against common but flawed practices like: Using P-values to select variables (Stepwise regression). Dropping "insignificant" variables from a final model.
Provides clear rules of thumb (like the 15-to-1 ratio) for how many variables a dataset can actually support. ⚖️ The Verdict Regression Modeling Strategies: With Applicatio...
Extensive use of restricted cubic splines to let the data dictate the shape of relationships. Harrell’s primary mission is to combat