Examining the effects of regression procedures on the temporal stability of parameter estimates in marketing models
Zoher E. Shipchandler D.B.A., James S. Moore Ph.D.
Journal of the Academy of Marketing Science · 1988 · Volume 16 · Issue 3
Abstract
This article investigates the temporal stability of parameter estimates by comparing the results obtained from ordinary least squares, ridge, and latent root regression techniques in two models plagued with ill-conditioned data. Ridge regression is found to provide improved individual coefficient stability through time and also to have slightly greater predictive accuracy beyond the original estimation period in both models. Temporal stability of marketing model parameters is important if the model is to prove useful to marketing decision makers in making inferences about the marginal impacts of individual predictor variables.
Keywords
Ordinary Little Square, Latent Vector, Ridge Regression, Ordinary Little Square Estimate, Ordinary Little Square Estimator
Enable JavaScript for citation tools and additional paper interactions.