๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

Evaluation of the predictive performance of biased regression estimators

โœ Scribed by David J. Friedman; Douglas C. Montgomery

Publisher
John Wiley and Sons
Year
1985
Tongue
English
Weight
546 KB
Volume
4
Category
Article
ISSN
0277-6693

No coin nor oath required. For personal study only.

โœฆ Synopsis

Regression models are widely used in forecasting, either directly as prediction equations, or indirectly as the basis of other procedures. The predictive performance of a regression model can be adversely affected by both multicollinearity and high-leverage data points. Although biased estimation procedures have been proposed as an alternative to least squares, there has been little analysis of the predictive performance of the resulting equations. This paper discusses the predictive performance of various biased estimators, emphasizing the concept that the predictive region, as well as the strength of the multicollinearity, dictates the choice of appropriate coefficient estimators.

๐Ÿ“œ SIMILAR VOLUMES

Some properties of a class of biased reg
Some properties of a class of biased regression estimators
โœ J.M. Lowerre ๐Ÿ“‚ Article ๐Ÿ“… 1977 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 731 KB

For the linear statistical model y = Xb + e, X of full column rank estimates of b of the form (C+ X'X)'X'y are studied, where C commutes with X'X and Q' is the Moore-Penrose inverse of Q. Such estimators may have smaller mean square error, component by component than does the least squares estimator