Article

Title: Skew-Normal-Cauchy Linear Mixed Models

Issue: Volume 81 Series B Part 2 Year 2019
Pages: 185 -- 202
Abstract
In this work, a flexible class of linear mixed models is introduced by assuming that the random effects and model errors follow a skew-normal-Cauchy distribution. The likelihood function and the information matrix based on of the observed data are computed. An EM-type algorithm is also proposed for estimating the parameters that seems to provide some advantages over a direct maximization of the likelihood function. Finally, the performance of the proposed model is evaluated numerically from simulated an real data.
Primary 62H10; Secondary 62F99, 62E99.
Keywords and phrases: EM-algorithm, Shape mixture, Skew-normal-cauchy distribution, Mixed effects model