A new generalized confidence interval for the among-group variance in the heteroscedastic one-way random effects model. Issue 3 (16th March 2017)

• Record Type: Journal Article
• Authors: Liu, Xuhua; Li, Na; Hu, Yuqin
• Is Part Of: Communications in statistics. Volume 46:Issue 3(2017)
• Page Start: 2299
• Page End: 3110
• Publication Date: 2017-03-16
• Subjects: Among-group variance component -- Fiducial generalized pivotal quantity -- Heteroscedastic -- One-way random effects model; 62F25; Mathematical statistics -- Periodicals; Mathematical statistics -- Data processing -- Periodicals; Digital computer simulation -- Periodicals; 519.5
• DOI: 10.1080/03610918.2015.1041975
• Languages: English
• ISSNs: 0361-0918

Abstract

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.