The purpose of this paper is to extend the linear mixed model for handling missing and {heavy-tailed} data. In this model, the random effects have multivariate mean mixture of normal distribution and errors arise from a multivariate normal distribution. An expectation conditional maximization algorithm is developed for parameter estimation based on missing information. The mechanism of missing data is missing-at-random. Simulation studies and real data sets represent the efficiency and performance of the proposed model.
Hashemi, F. and Goodarzi, F. (2024). Linear mixed model based on mean mixture of multivariate normal distributions: A flexible estimate based on missing value. Journal of Statistical Modelling: Theory and Applications, 5(2), 97-119. doi: 10.22034/jsmta.2025.22218.1160
MLA
Hashemi, F. , and Goodarzi, F. . "Linear mixed model based on mean mixture of multivariate normal distributions: A flexible estimate based on missing value", Journal of Statistical Modelling: Theory and Applications, 5, 2, 2024, 97-119. doi: 10.22034/jsmta.2025.22218.1160
HARVARD
Hashemi, F., Goodarzi, F. (2024). 'Linear mixed model based on mean mixture of multivariate normal distributions: A flexible estimate based on missing value', Journal of Statistical Modelling: Theory and Applications, 5(2), pp. 97-119. doi: 10.22034/jsmta.2025.22218.1160
CHICAGO
F. Hashemi and F. Goodarzi, "Linear mixed model based on mean mixture of multivariate normal distributions: A flexible estimate based on missing value," Journal of Statistical Modelling: Theory and Applications, 5 2 (2024): 97-119, doi: 10.22034/jsmta.2025.22218.1160
VANCOUVER
Hashemi, F., Goodarzi, F. Linear mixed model based on mean mixture of multivariate normal distributions: A flexible estimate based on missing value. Journal of Statistical Modelling: Theory and Applications, 2024; 5(2): 97-119. doi: 10.22034/jsmta.2025.22218.1160
)