On the Performance of the Exact F-test in Linear Mixed Models Involving Multiple Variance Components | ||||
| The Egyptian Statistical Journal | ||||
| Article 6, Volume 62, Issue 2, December 2018, Page 18-32 PDF (501.82 K) | ||||
| Document Type: Original Article | ||||
| DOI: 10.21608/esju.2018.314388 | ||||
 View on SCiNiTO | ||||
| Author | ||||
| Yahia S. El-Horbaty* | ||||
| Department of Mathematics, Insurance, and Applied Statistics, Helwan University | ||||
| Abstract | ||||
| Testing zero variance component in linear mixed models can be performed using an exact F-test. The test statistic is derived using a decomposition that is valid regardless of the unknown covariance structure of the random effects. The decomposition splits the log-likelihood function into two functions that repersent the between and within cluster variability in a traditional analysis of variance problem. Results from numerical simulatin studies reveal that F-test has a competing power compared to distribution free permutation tests. An application to real set is provided. | ||||
| Keywords | ||||
| Random effects; Exact test; Model selection; Log-likelihood function | ||||
|
Statistics Article View: 121 PDF Download: 238 |
||||
