Fig. 5

Cross-validation curve for selecting the optimal lambda in LASSO regression (Ten-fold cross-validation results for tuning the regularization parameter (λ) in the LASSO regression. The horizontal axis shows the log-transformed values of λ, and the vertical axis indicates the corresponding mean cross-validated error. Red dots represent the average error at each λ, with grey error bars showing the standard deviation. The number of non-zero coefficients at each λ is indicated at the top of the plot.)