TITLE

TESTING PREDICTED CHOICES AGAINST OBSERVATIONS IN PROBABILISTIC DISCRETE-CHOICE MODELS

AUTHOR(S)
Horowitz, Joel L.; Louviere, Jordan J.
PUB. DATE
June 1993
SOURCE
Marketing Science;Summer93, Vol. 12 Issue 3, p270
SOURCE TYPE
Academic Journal
DOC. TYPE
Article
ABSTRACT
Probabilistic discrete-choice models, such as multinomial logit models, are widely used to predict changes in market shares or total demand resulting from changes in policy variables under management control. These models often are evaluated in terms of their ability to predict choices in a holdout sample. This paper presents a new test for comparing predicted and observed choices. The results of a Monte Carlo experiment indicate that the new test has good finite-sample properties and high power in several circumstances likely to arise frequently -- applications.
ACCESSION #
4470427

 

Related Articles

  • ESTIMATING A MULTINOMIAL PROBIT MODEL OF BRAND CHOICE USING THE METHOD OF SIMULATED MOMENTS. Chintagunta, Pradeep K. // Marketing Science;Fall92, Vol. 11 Issue 4, p386 

    The multinomial probit model of brand choice is theoretically appealing for marketing applications as it is free from the "independence of irrelevant alternatives" property of the multinomial logit model. However, difficulties in estimation have restricted its widespread use in marketing. This...

  • Logit Demand Estimation Under Competitive Pricing Behavior: An Equilibrium Framework. Besanko, David; Gupta, Sachin; Jain, Dipak // Management Science;Nov98 Part 1 of 2, Vol. 44 Issue 11, p1533 

    Discrete choice models of demand have typically been estimated assuming that prices are exogenous. Since unobservable (to the researcher) product attributes, such as coupon availability, may impact consumer utility as well as price setting by firms, we treat prices as endogenous. Specifically,...

  • An Approach to the Measurement of Consumer Preferences Using Limited Information. Malhotra, Naresh K. // Journal of Marketing Research (JMR);Feb1986, Vol. 23 Issue 1, p33 

    The author proposes an alternative approach for measuring consumer preferences by using limited information. The approach differs from the current popular approaches in that once the nonpreferred choice alternatives are identified, no further information on them is obtained. Behavioral rationale...

  • Alternative Estimation Methods for Conjoint Analysis: A Monté Carlo Study. Wittink, Dick R.; Cattin, Philippe // Journal of Marketing Research (JMR);Feb1981, Vol. 18 Issue 1, p101 

    Conjoint analysis has been applied in a large number of commercial projects as well as in many noncommercial studies. Often MONANOVA, a nonmetric technique, is applied to a preference rank order obtained for a set of hypothetical objects. The authors report simulation results obtained for four...

  • A Comparison of the Internal Validity of Alternative Parameter Estimation Methods in Decompositional Multiattribute Preference Models. Jain, Arun K.; Acito, Franklin; Malhotra, Naresh K.; Mahajan, Vijay // Journal of Marketing Research (JMR);Aug1979, Vol. 16 Issue 3, p313 

    Since 1971, interest in the use of decompositional multiattribute preference models in marketing has been increasing. The applications have varied in terms of the type of data used, behavior predicted, and methods used for estimating parameters. The authors examine the effect of different data...

  • A Monté Carlo Comparison of Estimators for the Multinomial Logit Model. Bunch, David S.; Batsell, Richard R. // Journal of Marketing Research (JMR);Feb1989, Vol. 26 Issue 1, p56 

    The application of choice models continues to receive increasing attention in the marketing literature. Though new models are continually being developed and/or applied (Batsell and Polking 1985; Currim 1982; McFadden 1981; Tversky 1972a,b; Urban, Johnson, and Hauser 1984), the most widely used...

  • Model of Brand Choice with a No-Purchase Option Calibrated to Scanner-Panel Data. Chib, Siddhartha; Seetharaman, P.B.; Strijnev, Andrei // Journal of Marketing Research (JMR);May2004, Vol. 41 Issue 2, p184 

    In usual practice, researchers specify and estimate brand-choice models from purchase data, ignoring observations in which category incidence does not occur (i.e., no-purchase observations). This practice can be problematic if there are unobservable factors that affect the no-purchase and the...

  • Competitive Reactions to Market Entry: Explaining Interfirm Differences. Gatignon, Hubert; Anderson, Erin; Helsen, Kristiaan // Journal of Marketing Research (JMR);Feb1989, Vol. 26 Issue 1, p44 

    Competitive reactions are recognized as a driving force influencing marketing decisions. The authors seek to explain how established competitors in an oligopoly react to a significant new entry in their market. It has been suggested that at least some established competitors will react to a...

  • MODELING MULTIPLE SOURCES OF HETEROGENEITY IN MULTINOMIAL LOGIT MODELS: METHODOLOGICAL AND MANAGERIAL ISSUES. Gönül, Füsun; Srinivasan, Kannan // Marketing Science;Summer93, Vol. 12 Issue 3, p213 

    We offer a framework to specify and estimate various sources of heterogeneity m multinomial logit brand choice models. We let each brand-specific intercept and each parameter of the explanatory variable vector vary randomly across households. In addition, we distinguish loyal households from the...

Share

Read the Article

Courtesy of VIRGINIA BEACH PUBLIC LIBRARY AND SYSTEM

Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics