Normal view MARC view

Stochastic moderated regression: an efficient methodology for estimating parameters in moderated regression (RV 2005/30/MKT)

Author: Gatignon, Hubert ; Vosgerau, JoachimINSEAD Area: Marketing Series: Working Paper ; 2006/17/MKT (revised version of 2005/30/MKT) Publisher: Fontainebleau : INSEAD, 2006.Language: EnglishDescription: 30 p.Type of document: INSEAD Working Paper Online Access: Click here Abstract: In moderated regressions, the effect of a focal variable x1 depends on the level of a moderator variable x2. Moderation is estimated by introducing the product term of the two variables (x1x2) as an independent variable in the regression equation. Such moderator regressions often suffer from multicollinearity due to the usually high correlation between the product term and its components. We propose to recognize explicitly the stochastic nature of moderating effects to derive more efficient estimates of all the effects in the stochastic moderated regression model (SMR). Using Monte-Carlo simulations, we assess the ability to extract better inference about these effects under different conditions of stochasticity at different levels of the moderating effect. In addition, because of the inability to remove the collinearity inherent in the model specification itself (having a product term and its components in the same model), we evaluate the impact of introducing (or removing) terms in the model specification on the significance of these effects. Previous title: Moderating effects: the myth of mean centering - Gatignon, Hubert;Vosgerau, Joachim - 2005 - INSEAD Working Paper
Tags: No tags from this library for this title. Log in to add tags.
Item type Current location Collection Call number Status Date due Barcode Item holds
INSEAD Working Paper Digital Library
PDF Available BC007452
Total holds: 0

In moderated regressions, the effect of a focal variable x1 depends on the level of a moderator variable x2. Moderation is estimated by introducing the product term of the two variables (x1x2) as an independent variable in the regression equation. Such moderator regressions often suffer from multicollinearity due to the usually high correlation between the product term and its components. We propose to recognize explicitly the stochastic nature of moderating effects to derive more efficient estimates of all the effects in the stochastic moderated regression model (SMR). Using Monte-Carlo simulations, we assess the ability to extract better inference about these effects under different conditions of stochasticity at different levels of the moderating effect. In addition, because of the inability to remove the collinearity inherent in the model specification itself (having a product term and its components in the same model), we evaluate the impact of introducing (or removing) terms in the model specification on the significance of these effects.

Digitized

There are no comments for this item.

Log in to your account to post a comment.
Koha 18.11 - INSEAD Catalogue
Home | Contact Us | What's Koha?