The compression LS estimate of regression coefficient in multivariate linear model (Q1333840)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 640377
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | The compression LS estimate of regression coefficient in multivariate linear model |
scientific article; zbMATH DE number 640377 |
Statements
The compression LS estimate of regression coefficient in multivariate linear model (English)
0 references
6 February 1995
0 references
Compression least squares estimation of the regression coefficients is considered when the design matrix is near singularity in a multivariate linear model. The mean square error of the estimator is shown to be less than the mean square error of the least squares estimator of the regression coefficients by choosing proper tuning numbers. Besides, admissibility, numerical stability and relative efficiency of the compression least squares estimate are investigated, and a method of selecting the tuning number for practical use is suggested.
0 references
ridge estimation
0 references
compression least squares estimation
0 references
regression coefficients
0 references
multivariate linear model
0 references
mean square error
0 references
least squares estimator
0 references
tuning numbers
0 references
numerical stability
0 references
relative efficiency
0 references
0.7366478443145752
0 references
0.7341569066047668
0 references
