Figure 1
The figure consists of three stacked cross-validation plots for LASSO models predicting absence rate (Panel A), absence frequency (Panel B), and absence duration (Panel C). In each panel, the x-axis represents the regularization parameter (λ), and the y-axis represents the mean cross-validated error. A blue line with point markers shows the mean cross-validated error, and the shaded blue region represents the standard error. A red dashed vertical line marks λ.min, the value of λ that minimizes the cross-validated error, and a green dotted vertical line marks λ.1se, the largest value of λ within one standard error of the minimum. For absence rate and absence frequency, the cross-validated error remains nearly constant across a wide range of λ values before increasing at higher λ values. For absence duration, the minimum error occurs at a lower λ value, and the error increases more noticeably with stronger regularization.Cross-validation results for the LASSO models. Notes. Cross-validation curves showing the mean cross-validated error with standard error ribbons for different values of the regularization parameter (λ). Vertical dashed and dotted lines indicate the λ values that minimize the error (λ.min) and the most regularized model within one standard error of the minimum (λ.1se)