Improving the Predictive Power of Conjoint Analysis: The use of Factor Analysis and Cluster Analysis
Journal of Marketing ResearchPublished 1 May 1985
Michael R. Hagerty
Citations118
SJR quartileQ1
SJR score6.96
SNIP2.42
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This “optimal weighting” method is shown to perform better than cluster analysis and individual-level analysis in Monté Carlo examples and in real data.
Abstract
A method is derived to improve the predictive accuracy of conjoint analysis by grouping respondents with similar preferences. The often-used model of cluster analysis is shown to be inadequate because real respondents do not form densely packed clusters in preference space. The author then derives the best method of weighting respondents in the sense of maximizing predictive accuracy in conjoint analysis. This method turns out to be a form of Q -type factor analysis. This “optimal weighting” method is shown to perform better than cluster analysis and individual-level analysis in Monté Carlo examples and in real data. Optimal weighting is contrasted with other methods for improving conjoint analysis, and recommendations on their use are made.
Keywords
Decision SciencesAgricultural and Biological SciencesEconomics, Econometrics and Finance
PsychometrikaThe Approximation of One Matrix by Another of Lower Rank
3,795 Citations1936Carl Eckart, Gale Young
Journal of Consumer ResearchConjoint Analysis in Consumer Research: Issues and Outlook
3,197 Citations1978Paul E. Green, V. Srinivasan
Journal of Marketing ResearchCluster Analysis in Marketing Research: Review and Suggestions for Application
1,006 Citations1983Girish Punj, David W. Stewart
Journal of Marketing ResearchRecent Developments in Structural Equation Modeling
732 Citations1982Karl G. Jöreskog, Dag Sörbom
PsychometrikaLinear Programming Techniques for Multidimensional Analysis of Preferences
680 Citations1973V. Srinivasan, Allan D. Shocker
A new methodology for analyzing individual differences in preference judgments with regard to a set of stimuli prespecified in a multidimensional attribute space and Computational results show that the methodology for external analysis is “unbiased”—i.e., on an average it recovers the “true” ideal point and weights.
TechnometricsOrthogonal Main-Effect Plans for Asymmetrical Factorial Experiments
669 Citations1962Sidney Addelman
Journal of MarketingCommercial Use of Conjoint Analysis: A Survey
616 Citations1982Philippe C. Cattin, Dick R. Wittink
Journal of Mathematical BiologyNumerical taxonomy with fuzzy sets
581 Citations1974James C. Bezdek
A solution obtained without prior knowledge of labelled pattern structure is offered in support of contention that the fuzzy clustering technique proposed affords a comparatively reliable criterion for a posteriori evaluation of cluster validity.
Journal of Marketing ResearchRecent Developments in Structural Equation Modeling
487 Citations1982Karl G. Jöreskog, Dag Sörbom
Journal of Marketing ResearchHybrid Models for Conjoint Analysis: An Expository Review
282 Citations1984Paul E. Green
A classification of hybrid models is presented, followed by a review of their comparative performance in cross-validation tests, and Suggestions are offered on future studies that are essential before the role of hybrids in conjoint methods can be evaluated properly.
Journal of Marketing ResearchThe Application and Misapplication of Factor Analysis in Marketing Research
226 Citations1981David W. Stewart
The use of factor analysis as a method for examining the dimensional structure of data is contrasted with its frequent misapplication as a tool for identifying clusters and segments.
PsychometrikaAn Individual differences Model for Multidimensional Scaling
217 Citations1963Ledyard R Tucker, Samuel Messick
Journal of Marketing ResearchLevels of Aggregation in Conjoint Analysis: An Empirical Comparison
177 Citations1980William L. Moore
Journal of Marketing ResearchOverlapping Clustering: A New Method for Product Positioning
148 Citations1981Phipps Arabie, J. Douglas Carroll +2 more
An overlapping clustering model, ADCLUS, is described which can be used in marketing studies involving products/subjects that can belong to more than one group or cluster simultaneously.
Journal of Marketing ResearchAlternative Estimation Methods for Conjoint Analysis: A Monté Carlo Study
116 Citations1981Dick R. Wittink, Philippe C. Cattin
Simulation results obtained for four alternative estimation procedures suggest, within the limitations of the simulation study, that ANOVA may be the preferred procedure for compensatory models, whereas LINMAP is most likely to provide the best predictive validity for models with a dominant attribute.
PsychometrikaDetermining a Simple Structure When Loadings for Certain Tests are Known
112 Citations1939Charles I. Mosier
Journal of Marketing ResearchPooling Issues and Methods in Regression Analysis with Examples in Marketing Research
104 Citations1975Frank M. Bass, Dick R. Wittink
The issues associated with the decision of whether or not to pool the data for purposes of estimation are explored and examples of marketing applications are provided.
Journal of Marketing ResearchUsing Segmentation Approaches for Better Prediction and Understanding from Consumer Mode Choice Models
100 Citations1981Imran S. Currim
Empirical findings derived from data on consumers’ transportation preferences, perceptions, and choices in the San Francisco Bay area suggest that the models provide fairly accurate estimates of market share and that using the segmentation concept affords diagnostic and predictive advantages.
Journal of Marketing ResearchModeling an Organizational Buyer's Product Evaluation Strategy: Validity and Procedural Considerations
78 Citations1976Jerome E. Scott, Peter Wright
The subjective weights an organizational buyer gave to different cues were estimated by regression procedures with data from an in-office product-concept evaluation task to provide insight on the validity of cue-weighting evidence gathered under field conditions.
Journal of Marketing ResearchImproving Predictive Power of Conjoint Analysis by Constrained Parameter Estimation
71 Citations1983V. Srinivasan, Arun K. Jain +1 more
The prediction of first choice preferences by the full-profile method of conjoint analysis can be improved significantly by imposing constraints on parameters based on a priori knowledge of the ordering of part worths for different levels of an attribute.
Journal of MarketingComponential Segmentation in the Analysis of Consumer Trade-Offs
67 Citations1979Paul E. Green, Wayne S. DeSarbo
Journal of Marketing ResearchA Simple Bayesian Procedure for Estimation in a Conjoint Model
47 Citations1983Philippe C. Cattin, Alan E. Gelfand +1 more
Analytical results show that, with typical conjoint data, improvement may be expected over the estimation and prediction results obtained with ordinary least squares (OLS), and the expected improvement in prediction is confirmed by pilot empirical results.
Journal of Marketing ResearchA Note on the Reliability of Certain Clustering Algorithms
32 Citations1983G. Ray Funkhouser
The author's research suggests that unreliability may be a greater problem than has previously been suggested, especially with approaches involving large numbers of decisions about cluster membership.