Multicollinearity in regression: Review and examples
- 1 July 1982
- journal article
- research article
- Published by Wiley in Journal of Forecasting
- Vol. 1 (3) , 281-292
- https://doi.org/10.1002/for.3980010307
Abstract
When building regression models for forecasting, analysts often encounter the problem of multicollinearity or illconditioning in their data sets. In such cases, large variances and covariances can make subset selection and parameter estimation difficult to impossible. In this paper, we suggest several approaches for extending estimation results to forecasting and review theoretical results useful for forecasting with multicollinearity. Several examples are provided.Keywords
This publication has 44 references indexed in Scilit:
- Problems of Nonnormality and Multicollinearity for Forecasting Methods Based on Least SquaresA I I E Transactions, 1981
- A Simulation Study of Some Ridge EstimatorsJournal of the American Statistical Association, 1981
- Regression DiagnosticsPublished by Wiley ,1980
- Finite Sample Properties of Ridge EstimatorsTechnometrics, 1980
- Ridge Regression and James-Stein Estimation: Review and CommentsTechnometrics, 1979
- A Simulation Study of Alternatives to Ordinary Least SquaresJournal of the American Statistical Association, 1977
- Generalized mean squared error properties of regression estimatorsCommunications in Statistics - Theory and Methods, 1976
- Regressions by Leaps and BoundsTechnometrics, 1974
- The Relationship Between Variable Selection and Data Agumentation and a Method for PredictionTechnometrics, 1974
- A Critical View of Ridge RegressionJournal of the Royal Statistical Society: Series D (The Statistician), 1973