Bias of LS estimators in nonlinear regression models with constraints. Part I: General Case |
| |
Authors: | Andrej Pázman Jean-Baptiste Denis |
| |
Affiliation: | (1) Dept. of Probability and Statistics, Faculty of Mathematics and Physics, Commenius University, Mlynská dolina, 842 15 Bratislava, Slovakia;(2) Unité de Biométrie, INRA, F-78026 Versailles Cedex, France |
| |
Abstract: | We derive expressions for the asymptotic approximation of the bias of the least squares estimators in nonlinear regression models with parameters which are subject to nonlinear equality constraints.The approach suggested modifies the normal equations of the estimator, and approximates them up to op(N–1), where N is the number of observations. The bias equations so obtained are solved under different assumptions on constraints and on the model. For functions of the parameters the invariance of the approximate bias with respect to reparametrisations is demonstrated. Singular models are considered as well, in which case the constraints may serve either to identify the parameters, or eventually to restrict the parameter space. |
| |
Keywords: | nonlinear least squares maximum likelihood asymptotic bias nonlinear constraints transformation of parameters |
本文献已被 SpringerLink 等数据库收录! |
|