A new generalized confidence interval for the among-group variance in the heteroscedastic one-way random effects model |
| |
Authors: | Xuhua Liu Na Li Yuqin Hu |
| |
Affiliation: | 1. Department of Mathematics, China Agricultural University, Beijing, China;2. School of Management, University of the Chinese Academy of Sciences, Beijing, China;3. College of Applied Sciences, Beijing University of Technology, Beijing, China;4. School of Mathematics and Statistics, Zhejiang University of Finance &5. Economics, Hangzhou, China |
| |
Abstract: | Based on the generalized inference idea, a new kind of generalized confidence intervals is derived for the among-group variance component in the heteroscedastic one-way random effects model. We construct structure equations of all variance components in the model based on their minimal sufficient statistics; meanwhile, the fiducial generalized pivotal quantity (FGPQ) can be obtained through solving an implicit equation of the parameter of interest. Then, the confidence interval is derived naturally from the FGPQ. Simulation results demonstrate that the new procedure performs very well in terms of both empirical coverage probability and average interval length. |
| |
Keywords: | Among-group variance component Fiducial generalized pivotal quantity Heteroscedastic One-way random effects model |
|
|