Exercise

Residual standard error

Residual standard error (RSE) is a measure of the typical size of the residuals. Equivalently, it's a measure of how badly wrong you can expect predictions to be. Smaller numbers are better, with zero being a perfect fit to the data.

Again, you'll look at the models from the advertising pipeline, mdl_click_vs_impression_orig and mdl_click_vs_impression_trans. broom is loaded.

Instructions 1/3

undefined XP

1
2
3

Get the residual standard error for mdl_click_vs_impression_orig by glancing at the model, then pulling the sigma value.
Do the same for mdl_click_vs_impression_trans.