Figure 4.

The coefficient paths after (A) lasso, (B) elastic net, (C) ridge models. A line is drawn for each coefficient that traces its value over the searched values of the lasso penalty parameter λ on a reverse logarithmic scale. Lasso is letting variables into the model based on its penalty and the current value of λ. Cross-validation (CV) function (the mean deviance in the CV samples) is plotted over the search grid for the lasso penalty parameter λ on a reverse logarithmic scale for (D) lasso, (E) elastic net, (F) ridge models. The first λ tried is on the left, and the last λ tried is on the right.