A new generalized confidence interval for the among-group variance in the heteroscedastic one-way random effects model
| Autor: | Yu-Qin Hu, Xuhua Liu, Na Li |
|---|---|
| Rok vydání: | 2015 |
| Předmět: |
Statistics and Probability
Heteroscedasticity 05 social sciences Coverage probability Interval (mathematics) Variance (accounting) Random effects model Pivotal quantity 01 natural sciences Confidence interval 010104 statistics & probability Modeling and Simulation 0502 economics and business Statistics 0101 mathematics Sufficient statistic 050205 econometrics Mathematics |
| Zdroj: | Communications in Statistics - Simulation and Computation. 46:2299-3110 |
| ISSN: | 1532-4141 0361-0918 |
| DOI: | 10.1080/03610918.2015.1041975 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|