Inference robust to outliers with l1-norm penalization.

Jad Beyhum (1, 2)

1 UT Capitole - Université Toulouse Capitole
2 TSE-R - Toulouse School of Economics

This paper considers the problem of inference in a linear regression model with outliers where the number of outliers can grow with sample size but their proportion goes to 0. We apply the square-root lasso estimator penalizing the l1-norm of a random vector which is non-zero for outliers. We derive rates of convergence and asymptotic normality. Our estimator has the same asymptotic variance as the OLS estimator in the standard linear model. This enables to build tests and confidence sets in the usual and simple manner. The proposed procedure is also computationally advantageous as it amounts to solving a convex optimization program. Overall, the suggested approach constitutes a practical robust alternative to the ordinary least squares estimator.

Mots clés: Machine learning; high-dimensional statistics; square-root lasso; outliers; robust inference.

Domaines: Statistiques [math.ST]

Jad Beyhum. Inference robust to outliers with l1-norm penalization.. 2019. ⟨hal-02145401⟩