AN ALTERNATING LEAST‐SQUARES PROCEDURE FOR ESTIMATING MISSING PREFERENCE DATA IN PRODUCT‐CONCEPT TESTING*

Product-concept testing is a popular activity in marketing research. Often the number of new product/service concepts under study far exceeds the time available for any single respondent. Respondents therefore may receive only a subset of the concepts comprising the total design. Researchers are interested in making plausible imputations for the missing evaluations of any given respondent.This paper proposes a model and an iterative estimation procedure to impute missing entries for each evaluator. The model and the procedure incorporate (1) the internal structure of the response matrix arid (2) an ancillary matrix of (nonmissing) respondent background data; they also (3) allow for individual differences in respondents’ uses of the numerical rating scale. The model is applied to both real and synthetic data. Suggestions also are given on how the data imputations may be used in market segmentation and product-line decisions.

[1]  Roger M. Heeler,et al.  Analysis of Contingency Tables with Sparse Values , 1979 .

[2]  William G. Cochran,et al.  Experimental designs, 2nd ed. , 1957 .

[3]  Edgar A. Pessemier.  Product Management: Strategy and Organization , 1982 .

[4]  William R. Dillon,et al.  Analyzing Qualitative Predictors with Too Few Data: An Alternative Approach to Handling Sparse-Cell Values , 1981 .

[5]  Paul E. Green,et al.  On the Design of Choice Experiments Involving Multifactor Alternatives , 1974 .

[6]  George W. Furnas,et al.  The estimation of ultrametric and path length trees from rectangular proximity data , 1984 .

[7]  D. Rubin,et al.  On Jointly Estimating Parameters and Missing Data by Maximizing the Complete-Data Likelihood , 1983 .

[8]  M. J. Box,et al.  Missing Values in Multiresponse Nonlinear Model Fitting , 1970 .

[9]  Prem K. Goel,et al.  Estimation of the Correlation Coefficient from a Broken Random Sample , 1980 .

[10]  Richard Staelin,et al.  A proposal for handling missing data , 1975 .

[11]  R. Bargmann,et al.  MAXIMUM LIKELIHOOD ESTIMATION WITH INCOMPLETE MULTIVARIATE DATA , 1964 .

[12]  Wayne S. DeSarbo,et al.  Three-Way Multivariate Conjoint Analysis , 1982 .

[13]  Donald B. Rubin,et al.  A Non‐Iterative Algorithm for Least Squares Estimation of Missing Values in Any Analysis of Variance Design , 1972 .

[14]  S. Addelman.  Orthogonal Main-Effect Plans for Asymmetrical Factorial Experiments , 1962 .

[15]  John A. Hartigan,et al.  Clustering Algorithms , 1975 .

[16]  D. Rubin.  INFERENCE AND MISSING DATA , 1975 .

[17]  Raymond F. Koopman.  Fast regression estimates of missing data , 1976 .

[18]  Neil H. Timm,et al.  The estimation of variance-covariance and correlation matrices from incomplete data , 1970 .

[19]  T. W. Anderson.  Maximum Likelihood Estimates for a Multivariate Normal Distribution when Some Observations are Missing , 1957 .

[20]  W. DeSarbo,et al.  Componential Segmentation in the Analysis of Consumer Trade-Offs , 1979 .

[21]  Anderson Rl,et al.  Missing-plot techniques. , 1946 .

[22]  Y. Haitovsky.  Missing Data in Regression Analysis , 1968 .

[23]  Donald B. Rubin,et al.  Characterizing the Estimation of Parameters in Incomplete-Data Problems , 1974 .

[24]  J. Frane.  Some simple procedures for handling missing data in multivariate analysis , 1976 .

[25]  Alastair Scott,et al.  Missing Variables in Bayesian Regression II. , 1976 .

[26]  M. S. Bartlett,et al.  Some examples of statistical methods of research in agriculture and applied biology , 1937 .

[27]  William L. Moore,et al.  Levels of Aggregation in Conjoint Analysis: An Empirical Comparison , 1980 .

[28]  R. R. Hocking,et al.  The analysis of incomplete data. , 1971 .

[29]  George L. Edgett.  Multiple Regression with Missing Observations Among the Independent Variables , 1956 .

[30]  M. Glasser,et al.  Linear Regression Analysis with Missing Observations among the Independent Variables , 1964 .