Title: The MLE-3D algorithm for the 2-fold growth curve model
Authors: Joseph Nzabanita - University of Rwanda (Rwanda) [presenting]
Dietrich von Rosen - Swedish University of Agricultural Sciences (Sweden)
Martin Singull - Linkoping University (Sweden)
Abstract: There is a growing interest in the analysis of multi-way data. In many studies the inference about the dependencies in three-way data is done using the third order tensor normal model, where the focus is on the estimation of the variance-covariance matrix which has a Kronecker product structure. Little attention is paid to the structure of the mean, though, there is a potential to improve the analysis by assuming a structured mean. Assuming a trilinear structure for the mean in the tensor normal model, a 2-fold growth curve model is formulated and a maximum likelihood estimation based algorithm for estimating parameters is proposed. Simulation studies show that the proposed algorithm performs well.