论文信息 - Shrinking Towards Subspaces in Multiple Linear Regression

Shrinking Towards Subspaces in Multiple Linear Regression

The problem of multiple linear regression and the use of shrinkage estimators is considered. It is pointed out that sometimes prior beliefs, about the signs and orders of magnitude of the regression coefftcients, for example, suggest a subspace L such that it is more natural to shrink the least squares estimate towards its projection onto L than towards the origin. An empirical Bayes approach is used to construct such an estimator for an arbitrary design matrix. The estimator is illustrated on the acetylene data previously analyzed by Marquardt and Snee (1975).

Samuel D. Oman | S. Oman

[1] R. Snee,et al. Ridge Regression in Practice , 1975 .

[2] J. Rolph. Choosing shrinkage estimators for regression problems , 1976 .

[3] M. Goldstein. Bayesian analysis of regression problems , 1976 .

[4] Norman R. Draper,et al. Ridge Regression and James-Stein Estimation: Review and Comments , 1979 .

[5] C. Morris,et al. Non-Optimality of Preliminary-Test Estimators for the Mean of a Multivariate Normal Distribution , 1972 .

[6] B. Efron,et al. Stein's Estimation Rule and Its Competitors- An Empirical Bayes Approach , 1973 .

[7] W. Massy. Principal Components Regression in Exploratory Statistical Research , 1965 .

[8] M. Kendall. A course in multivariate analysis , 1958 .

[9] B. Efron,et al. Empirical Bayes on vector observations: An extension of Stein's method , 1972 .

[10] Grace M. Carter,et al. Empirical Bayes Methods Applied to Estimating Fire Alarm Probabilities , 1974 .

[11] B. Efron,et al. Data Analysis Using Stein's Estimator and its Generalizations , 1975 .

[12] Stanley L. Sclove,et al. Improved Estimators for Coefficients in Linear Regression , 1968 .