Biometrical Letters Vol. 58(1), 2021, pp. 69-79
|
PROPERTIES OF AN MLE ALGORITHM FOR THE MULTIVARIATE LINEAR MODEL WITH A SEPARABLE COVARIANCE MATRIX STRUCTURE Anna Szczepanska-Álvarez1, Bogna Zawieja1, Adolfo Álvarez2 1Department of Mathematical and Statistical Methods, Poznan University of Life Sciences, Wojska Polskiego 28, PL-60-637 Poznan, Poland, e-mail:anna.szczepanska-alvarez@up.poznan.ple-mail: bogna.zawieja@up.poznan.pl 2Collegium Da Vinci, Department of Informatics and Visual Communication, ul. Kutrzeby 10, 61-719 Poznan, Poland, e-mail:adolfo.alvarez-pinto@cdv.pl |
In this paper we present properties of an algorithm to determine the maximum likelihood estimators of the covariance matrix when two processes jointly affect the observations. Additionally, one process is partially modeled by a compound symmetry structure. We perform a simulation study of the properties of an iteratively determined estimator of the covariance matrix.
compound symmetry structure, Kronecker product, maximum likelihood estimation, convergence of algorithm, bias of estimator
