ISSN:
1435-926X
Keywords:
Key words: Generalized linear model
;
prediction
;
missing observations
Source:
Springer Online Journal Archives 1860-2000
Topics:
Mathematics
Notes:
Abstract. In the present paper we propose a direct approach to prediction in the linear model E[Y]=Xβ, where some but not all of the coordinates of Y are observable, X is a known design matrix, β is an unknown parameter vector, and Var[Y] is known and positive definite. To construct a predictor Y * 2 of the non-observable part Y 2 of Y such that E[Y * 2]=E[Y 2] and Y * 2=B * Y 1, where B * is a matrix and Y 1 is the observable part of Y, we minimize the expected weighted loss over all estimators of β which are unbiased and linear in Y 1. The predictor Y * 2 is then obtained from a canonical decomposition of the expected loss into an approximation part for Y 1 and a prediction part for Y 2.
Type of Medium:
Electronic Resource
URL:
http://dx.doi.org/10.1007/s001840050011
Permalink