Inputs mirror those of ridge: n observations, p predictors (standardized to unit variance), and a dependent variable y. Typical macro applications involve p ranging from 50 to 500 candidate predictors: monthly financial variables, survey indices, labor market indicators, international series, and their lags. The critical difference from ridge is that the analyst expects only a subset - perhaps 5 to 20 - of these predictors to be active in the true model.
The model solves minβ2n1∥y−Xβ∥22+λ∑j=1p∣βj∣. The L1 penalty creates a non-smooth optimization landscape. At each coordinate j, the solution is β^j=S(zj,λ) where zj is the partial residual regression coefficient and S(z,λ)=sign(z)(∣z∣−λ)+ is the soft-thresholding operator. If ∣zj∣≤λ, the coefficient is set exactly to zero. If ∣zj∣>λ, it is shrunk toward zero by λ. The entire algorithm cycles through coordinates repeatedly until all coefficients stabilize.
Penalty selection uses k-fold cross-validation, typically k=10. The CV curve plots prediction error against log(λ), and the minimum identifies λmin. The one-standard-error rule picks λ1SE, the largest λ within one SE of the minimum - a more parsimonious model that protects against overfitting. For time-series data, the CV folds must respect temporal ordering (rolling or expanding window). Information criteria (BIC, extended BIC) are alternatives that penalize model complexity directly and avoid the need for cross-validation.