Modeling Customer Survey Data
In customer value analysis (CVA), a company conducts sample surveys of its customers and of its competitors’ customers to determine the relative performance of the company on many attributes ranging from product quality and technology to pricing and sales support. The data discussed in this paper are from a quarterly survey run at Lucent Technologies.
We have built a Bayesian model for the data that is partly hierarchical and has a time series component. By “model” we mean the full specification of information that allows the computation of posterior distributions of the data — sharp specifications such as independent errors with normal distributions and diffuse specifications such as probability distributions on parameters arising from sharp specifications. The model includes the following: (1) survey respondent effects are modeled by random location and scale effects, a t-distribution for the location and a Weibull distribution for the scale; (2) company effects for each attribute through time are modeled by integrated sum-difference processes; (3) error effects are modeled by a normal distribution whose variance depends on the attribute; in the model, the errors are multiplied by the respondent scale effects.
The model is the first full description of CVA data; it provides both a characterization of the performance of the specific companies in the survey as well as a mechanism for studying some of the basic notions of CVA theory.
Building the model and using it to form conclusions about CVA, stimulated work on statistical theory, models, and methods: (1) a Bayesian theory of data exploration that provides an overall guide for methods used to explore data for the purpose of making decisions about model specifications; (2) an approach to modeling random location and scale effects in the presence of explanatory variables; (3) a reformula-tion of integrated moving-average processes into integrated sum-difference models, which enhances interpretation, model building, and computation of posterior distri-butions; (4) post-posterior modeling to combine certain specific exogenous information — information from sources outside of the data — with the information in a posterior distribution that does not incorporate the exogenous information; (5) trellis display, a framework for the display of multivariable data.
KeywordsPosterior Distribution Markov Chain Monte Carlo Royal Statistical Society Supply Company Model Building Process
Unable to display preview. Download preview PDF.
- Bradlow, E. T. and Zaslaysky (1997). A Hierarchical Latent Variable Model for Ordinal Data from a Customer Satisfaction Survey with “No Answer” Responses. Technical Report, Department of Marketing, Wharton School, University of Pennsylvania.Google Scholar
- Cleveland, W. S. (1993). Visualizing Data, Hobart Press, firstname.lastname@example.org.Google Scholar
- Cleveland, W. S., Denby, L., and Liu, C. (1998). Random Location and Scale Models for Case Data, in preparation.Google Scholar
- Cleveland, W. S. and Liu, C. (1998a). A Theory of Model Building, in preparation.Google Scholar
- Cleveland, W. S. and Liu, C. (1998b). Integated Sum-Difference Time Series Models, in preparation.Google Scholar
- Dempster, A. P. (1970). Foundation of Statistical Inference, Proceedings of the Symposium of the Foundations of Statistical Inference, March 31 to April 9, 56–81.Google Scholar
- Gale, B. T. (1994). Managing Customer Value, MacMillan, New York.Google Scholar
- Gelman, A., King, G., and Liu, C. (1998). Multiple Imputation for Multiple Surveys (with discussion), Journal of the American Statistical Association, to appear.Google Scholar
- Good, I. J. (1957). Mathematical Tools, Uncertainty and Business Decisions, edited by Carter, C. F., Meredith, G. P., and Shackle, G. L. S., 20–36, Liverpool University Press.Google Scholar
- Hill, B. M. (1990). A Theory of Bayesian Data Analysis, Bayesian and Likelihood Methods in Statistics and Econometrics, S. Geiser, J. S. Hodges, S. J. Press and A. Zellner (Editors), 49–73, Elsevier Science Publishers B. V. (North-Holland).Google Scholar
- Naumann, E. and Kordupleski, R. (1995). Customer Value Toolkit, International Thomson Publishing, London.Google Scholar
- Pinheiro, J., Liu, C., and Wu, Y. (1997). Robust Estimation in Linear Mixed-Effects Models Using the Multivariate t-distribution, Technical Report, Bell Labs.Google Scholar
- Savage, L. J. (1961). The Subjective Basis of Statistical Practice, unpublished book manuscript.Google Scholar
- Best, N.G., Spiegelhalter, D.J., Thomas, A. and Brayne, C.E.G. (1996). Bayesian analysis of realistically complex models. Journal of the Royal Statistical Society, Series A 159, 323–342Google Scholar
- Gelfand, A.E., Dey, D.K. and Chang, H. (1992). Model determination using predictive distributions with implementation via sampling-based methods. In Bayesian Statistics 4 (eds. J.M. Bernardo, J.O. Berger, A.P. Dawid and A.F.M. Smith), pp. 147–167. Oxford: Oxford University Press.Google Scholar
- Goldstein, H. and Spiegelhalter, D.J. (1996). Statistical aspects of institutional performance: league tables and their limitations (with discussion). Journal of the Royal Statistical Society, Series A 159Google Scholar
- Spiegelhalter, D.J., Thomas, A. and Best, N.G. (1995a). Computation on Bayesian graphical models. In Bayesian Statistics 5 (eds. J.M. Bernardo, J.O. Berger, A.P. Dawid and A.F.M. Smith), pp. 407–425. Oxford: Clarendon Press.Google Scholar
- Spiegelhalter, D.J., Thomas, A., Best, N.G. and Gilks, W.R. (1995b). BUGS Bayesian inference Using Gibbs Sampling: Version 0.5, MRC Biostatistics Unit, Cambridge.Google Scholar
- Bradlow, E.T. (1994), Analysis of Ordinal Survey Data with ‘No Answer’ Responses, Doctoral Dissertation, Department of Statistics, Harvard University.Google Scholar
- Bradlow, E.T. and Zaslaysky, A.M., A Hierarchical Model for Ordinal Customer Satisfaction Data with “No Answer” Responses, unpublished manuscript.Google Scholar
- Cleland Alan S. and Alebert V. Bruno (1997), The Market Value Process: Bridging Customer and Shareholder Value, San Francisco: Jossey-Bass Publishers.Google Scholar
- Gale, Bradley T. (1994), Managing Customer Value: Creating Quality & Service that Customers Can See, New York: The Free Press.Google Scholar
- Slywotzski, Adrian J. (1996), Value Migration: How to think Several Moves Ahead of the Competition, Boston: Harvard Business School Press.Google Scholar
- Liu, C. and Rubin, D. B. (1998). Markov-Normal analysis of iterative simulations before their convergence: reconsideration and application, Technical Report, Bell-Labs, Lucent Technologies and Department of Statistics, Harvard Univ.Google Scholar