Accession Number : AD0729033

Title :   Optimal Linear Prediction,

Corporate Author : PRINCETON UNIV N J DEPT OF STATISTICS

Personal Author(s) : Watson,G. S.

Report Date : 1971

Pagination or Media Count : 8

Abstract : Necessary and sufficient conditions are given so that, for the most general regression model, Y = X(beta) + u the least squares estimator of (X' sub zero)Beta is the same as the best linear unbiased predictor of (y sub zero) = (X' sub zero)beta + (u sub zero). (Author)

Descriptors :   (*REGRESSION ANALYSIS, MATHEMATICAL PREDICTION), LEAST SQUARES METHOD, MATHEMATICAL MODELS, TIME SERIES ANALYSIS, THEOREMS

Subject Categories : Statistics and Probability

Distribution Statement : APPROVED FOR PUBLIC RELEASE