Part 2. Marketing Research
Published Online: 15 DEC 2010
Copyright © 2011 John Wiley & Sons, Ltd. All rights reserved.
Wiley International Encyclopedia of Marketing
How to Cite
Arora, N. 2010. Logit Model. Wiley International Encyclopedia of Marketing. 2.
- Published Online: 15 DEC 2010
Consumer choice is arguably the most important variable in marketing. Examples include brand choice in a grocery store purchase, selection of a kitchen appliance at a retailer, or choosing a health club from the available alternatives. Choice is a discrete variable (taking a 0–1 value) and therefore does not lend itself to a linear regression model, where the dependent variable is continuous. The logit model is of great value because it allows a manager to understand the link between marketing actions and consumer behavior. For example, the model can be used to conduct a “what if” analysis for a price change, an in-store display, or a coupon drop. Two popular application areas for the logit model in marketing include household level panel data and choice-based conjoint analysis. While enormously popular, the logit model has limitations. First, the distribution assumption for the error term is fairly ad hoc and results in an undesirable property called the IIA or independence of irrelevant alternatives property. A second limitation is the implicit assumption that consumers use a compensatory evaluation process in selecting an alternative. It is certainly plausible that consumers, in certain contexts, may use a noncompensatory evaluation process. Several solutions to both these problems have been proposed.
- random utility;
- market share;