We propose a new lasso-type estimator of regression coefficients for regression models. Our proposal relies on the recent idea of induced smoothing and leads to estimators with sampling distribution somewhat close to the Normal one, regardless of their true value, along with the corresponding reliable covariance matrix. As a consequence inference (e.g. p-values) may be carried out relatively easily. We present results from some simulation experiments.
|Numero di pagine||6|
|Stato di pubblicazione||Published - 2016|