Maximal skewness projections for scale mixtures of skew-normal vectors

TL;DR

This paper investigates the maximal skewness projection in scale mixtures of skew-normal vectors, revealing that under certain conditions, the optimal direction aligns with the shape vector, aiding skewness analysis.

Contribution

It provides a theoretical foundation for identifying the maximal skewness projection in SMSN distributions, linking it to the shape vector under specific moment conditions.

Findings

Maximal skewness direction is proportional to the shape vector under certain conditions.

Theoretical results are validated with examples from SMSN distributions.

Simulation experiments demonstrate practical usefulness of the findings.

Abstract

Multivariate scale mixtures of skew-normal (SMSN) variables are flexible models that account for non-normality in multivariate data scenarios by tail weight assessment and a shape vector representing the asymmetry of the model in a directional fashion. Its stochastic representation involves a skew-normal (SN) vector and a non negative mixing scalar variable, independent of the SN vector, that injects kurtosis into the SMSN model. We address the problem of finding the maximal skewness projection for vectors that follow a SMSN distribution; when simple conditions on the moments of the mixing variable are fulfilled, it can be shown that the direction yielding the maximal skewness is proportional to the shape vector. This finding stresses the directional nature of the asymmetry in this class of distributions; it also provides the theoretical foundations for solving the skewness model based projection pursuit for SMSN vectors. Some examples that show the validity of our theoretical findings for the most famous distributions within the SMSN family are also given. For the sake of completeness we carry out a simulation experiment with artificial data, which sheds light on the usefulness and implications of our result in the statistical practice.