Estimation and diagnostics in nested variance component models /

Bibliographic Details
Main Author:	Von Tress, Mark Scott, 1952-
Other Authors:	Longnecker, Michael T. (degree committee member.), Matis, James H. (degree committee member.), Williams, Glen N. (degree committee member.)
Format:	Thesis Book
Language:	English
Published:	1987.
Subjects:	Analysis of variance. Linear models (Statistics) Major statistics. Academic theses
Online Access:	Link to ProQuest copy Link to OAKTrust copy ProQuest, Abstract

Description
Abstract:	Estimation and diagnostics in nested variance component models is researched in this dissertation. Sufficiency and completeness of the statistics in nested models is studied to build the foundation for efficient estimators of the variance components. Information inequalities for unbiased estimators of the parameters in nested random models are studied next so that the efficiencies of different estimators may be compared. Several point estimates are presented for the variance components of the one-way and two-fold nested random models. Each of the estimators are compared on the basis of efficiency. Confidence intervals are presented next. Finally diagnostics are studied in order to asses the effect of the individual data on the ANOVA estimators.
Item Description:	"Major subject: Statistics." Typescript (photocopy). Vita.
Physical Description:	ix, 161 leaves ; 29 cm
Bibliography:	Includes bibliographical references (leaves 146-151).