Robust Model Selection for Finite Mixture of Regression Models Through Trimming

Abstract

In this article, we introduce a new variable selection technique through trimming for finite mixture of regression models. Compared to the traditional variable selection techniques, the new method is robust and not sensitive to outliers. The estimation algorithm is introduced and numerical studies are conducted to examine the finite sample performance of the proposed procedure and to compare it with other existing methods.

References in corpus (2)

• Nearly unbiased variable selection under minimax concave penalty
• Semiparametric Mixtures of Regressions with Single-index for Model Based Clustering