Improved prediction in the presence of multicollinearity

DOI10.1016/0304-4076(87)90082-0zbMath0617.62054OpenAlexW2041268520MaRDI QIDQ1822169

R. Carter Hill, George G. Judge

Publication date: 1987

Published in: Journal of Econometrics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0304-4076(87)90082-0

zbMATH Keywords

James-Stein estimatorMonte Carlo experimentminimax estimatorsmulticollinearityprincipal components estimatorcomparison of estimatorssampling performancecharacteristic root spectrumMundlak's pre-test estimatornon-minimax pretest rulepartitioned limited translation estimatorssquared error of prediction lossStein- like rules

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Estimation in multivariate analysis (62H12) Ridge regression; shrinkage estimators (Lasso) (62J07) Linear regression; mixed models (62J05) Probabilistic methods, stochastic differential equations (65C99)

Related Items (12)

Admissibility of linear estimators of the common mean parameter in general linear models under a balanced loss function ⋮ The principal correlation components estimator and its optimality ⋮ A comparison of stein-like procedures for estimating linear regression models with multicollinear data ⋮ Large sample asymptotic properties of the double k-class estimators in linear regression models ⋮ New Bayesian approach to the estimation in simultaneous equations model ⋮ Generalized Liu Type Estimators Under Zellner's Balanced Loss Function ⋮ Admissibility for linear estimators of regression coefficient in a general Gauss-Markoff model under balanced loss function ⋮ Improved estimation under collinearity and squared error loss ⋮ Double \(k\)-class estimators in regression models with non-spherical disturbances ⋮ Robustness of Stein-type estimators under a non-scalar error covariance structure ⋮ On generalized ridge regression estimators under collinearity and balanced loss ⋮ A monte carlo study of collinearity in linear simultaneous equation models^∗

Cites Work

• Unnamed Item
• Unnamed Item
• On the concept of non-significant functions and its implications for regression analysis
• Estimation of the mean of a multivariate normal distribution
• Inadmissibility of maximum likelihood estimators in some multiple regression problems with three or more independent variables
• On Truncation of Shrinkage Estimators in Simultaneous Estimation of Normal Means
• Component selection norms for principal components regression
• An Optimal Property of Principal Components in the Context of Restricted Least Squares
• Stein's Estimation Rule and Its Competitors--An Empirical Bayes Approach
• Limiting the Risk of Bayes and Empirical Bayes Estimators--Part II: The Empirical Bayes Case

This page was built for publication: Improved prediction in the presence of multicollinearity