On the Efficiency of Maximum Likelihood and Restricted Maximum Likelihood Estimators for Linear Mixed Effects Models

In this work, the performances of maximum likelihood (ML) and restricted maximum likelihood (REML) estimation of linear mixed effects models were examined. The behaviours and properties of the ML and REML methods of estimating the variance-covariance components in linear mixed effects models were studied via Monte-Carlo experiment. Results revealed that both estimation techniques yielded the same estimates of the fixed effects parameters. However, ML estimates of variance-covariance components, especially for the random effects terms were more biased downwards than the REML counterparts. It was also discovered that the biasness of the ML estimates for the variance-covariance components increase as the number of fixed effects parameters in the model increase.

Citation

3. Yahya W. B, Adeniyi I. A, Olayemi R. M, Dauda K. A, Banjoko, A. W, Olorede K. O. and Ezenweke C. P. (2016). On the Efficiency of Maximum Likelihood and Restricted Maximum Likelihood Estimators for Linear Mixed Effects Models. Nigerian Journal of Mathematics and Applications. Mathematical Association of Nigeria (MAN), Vol. 25, 19 − 55. URL: https://tinyurl.com/44e3jxst

URI

https://kwasuspace.kwasu.edu.ng/handle/123456789/5463

Collections

Scholarly Publication

Full item page