The unbalanced nested error component regression model

This paper considers a nested error component model with unbalanced data an d proposes simple analysis of variance (ANOVA). maximum likelihood (MLE) an d minimum norm quadratic unbiased estimators (MINQUE)-type estimators of th e variance components. These are natural extensions from the biometrics, st atistics and econometrics literature. The performance of these estimators i s investigated by means of Monte Carlo experiments. While the MLE and MINQU E methods perform the best in estimating the variance components and the st andard errors of the regression coefficients, the simple ANOVA methods perf orm just as well in estimating the regression coefficients. These estimatio n methods are also used to investigate the productivity of public capital i n private production. (C) 2001 Published by Elsevier science S.A.