臺灣博碩士論文加值系統

聯合分析法(Conjoint analysis)能夠衡量顧客對於產品不同屬性的偏好，並能協助公司建立市場模型來預測市佔率、盈餘、甚至新產品進入市場後的預期獲利。但是公司可能需要花費大量的時間和金錢以收集到足夠的資料，因此在實務上該如何用較少的問卷資料還原同樣質量的顧客異質性是相當重要的課題。本研究提出結合複合屬性的修正模型以縮短問卷量，並嘗試利用二階段階層貝氏模型還原複合屬性背後的潛藏偏好，以協助我們做出更精確的預測以及對於顧客偏好更全面的了解。本研究比較了修正模型以及原始模型的表現，修正模型在樣本內預測的表現勝過原始模型，但修正模型在樣本外預測的表現不及原始模型。

Conjoint analysis can measure consumers'' preference (part-worths) for different features of a product, which can help the companies to create market models that estimate market share, revenue and even profitability of newly-designed products or services. However, in order to gather enough information, the process of data-collecting can be time-consuming and cost lots of money, so practitioners would be eager to find a way to recover the heterogeneity in the part-worths with shorter questionnaires. In our study, we proposed a modified model using complex attribute to shorten the questionnaires. Also, we tried to recover latent part-worths behind the complex attribute with the use of two-stage hierarchical Bayesian model, which may help us make better predictions and better understanding the part-worths of customers. Compared to the original model, the modified model performed better at in-sample prediction, however, modified model performed weaker than original model at out-sample prediction.

口試委員會審定書 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . i
誌謝 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ii
摘要 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iv
Abstract . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . v
Contents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . vi
List of Figures . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . viii
List of Tables . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . x
1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.1 Background . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.2 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
1.3 Goal . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
1.3.1 Prediction - Higher Hit Rate . . . . . . . . . . . . . . . . . . . . 5
1.3.2 Description - Interpretation of Each Attribute Level . . . . . . . . 5
1.4 Framework . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
2 Literature Review . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
2.1 Conjoint Analysis . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
2.1.1 Choice-Based Conjoint Analysis . . . . . . . . . . . . . . . . . . 7
2.1.2 Hierarchical Bayesian Conjoint Analysis . . . . . . . . . . . . . 8
2.2 Questionnaire Design . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
2.3 Measurement and Estimation of Conjoint Utility . . . . . . . . . . . . . . 10
3 Model Specification . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
3.1 Basis Structure . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
3.2 Random Utility Model . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
3.3 Multinomial Logit Model . . . . . . . . . . . . . . . . . . . . . . . . . . 16
3.4 Hierarchical Bayesian Model . . . . . . . . . . . . . . . . . . . . . . . . 17
3.5 Modified Hierarchical Bayesian MNL Model . . . . . . . . . . . . . . . 19
3.6 Parameter Estimation . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20
4 Empirical Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23
4.1 Data . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23
4.1.1 Data Access . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23
4.1.2 Experiment Design . . . . . . . . . . . . . . . . . . . . . . . . . 23
4.1.3 Data Preparation . . . . . . . . . . . . . . . . . . . . . . . . . . 27
4.1.4 Data Splitting . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28
4.1.5 Data Exploration . . . . . . . . . . . . . . . . . . . . . . . . . . 28
4.2 Estimation Result . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30
4.2.1 Hierarchical Bayesian MNL Model . . . . . . . . . . . . . . . . 32
4.2.2 Modified Hierarchical Bayesian MNL Model . . . . . . . . . . . 35
4.3 Prediction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 42
4.3.1 Prediction Architecture . . . . . . . . . . . . . . . . . . . . . . . 42
4.3.2 Prediction Comparison . . . . . . . . . . . . . . . . . . . . . . . 46
5 Conclusions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 52
5.1 Limitation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 52
5.2 Future Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 54
Bibliography . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 56

Adams, L. L. M. and Gale, D. (1982). Solving the quandary between questionnaire length and response rate in educational research. Research in Higher Education, 17(3):231– 240.
Allenby, G. M., Arora, N., and Ginter, J. L. (1995). Incorporating prior knowledge into the analysis of conjoint studies. Journal of Marketing Research, pages 152–162.
Allenby, G. M., Arora, N., and Ginter, J. L. (1998). On the heterogeneity of demand. Journal of Marketing Research, pages 384–389.
Andrews, R. L., Ansari, A., and Currim, I. S. (2002). Hierarchical bayes versus finite mixture conjoint analysis models: A comparison of fit, prediction, and partworth recovery. Journal of Marketing Research, 39(1):87–98.
Bean, A. G. and Roszkowski, M. J. (1995). The long and short of it. Marketing Research, 7(1):20.
Berdie, D. R. (1989). Reassessing the value of high response rates to mail surveys. Marketing Research, 1(3).
Brooks, S. P. and Gelman, A. (1998). General methods for monitoring convergence of iterative simulations. Journal of computational and graphical statistics, 7(4):434–455.
Chib, S. and Greenberg, E. (1995). Understanding the metropolis-hastings algorithm. The american statistician, 49(4):327–335.
DeSarbo, W. S., Ramaswamy, V., and Cohen, S. H. (1995). Market segmentation with choice-based conjoint analysis. Marketing Letters, 6(2):137–147.
Dillman, D. A., Sinclair, M. D., and Clark, J. R. (1993). Effects of questionnaire length, respondent-friendly design, and a difficult question on response rates for occupantaddressed census mail surveys. Public Opinion Quarterly, 57(3):289–304.
Gelman, A. and Rubin, D. B. (1992). Inference from iterative simulation using multiple sequences. Statistical science, pages 457–472.
Geman, S. and Geman, D. (1984). Stochastic relaxation, gibbs distributions, and the bayesian restoration of images. IEEE Transactions on pattern analysis and machine intelligence, (6):721–741.
Green, P. E. and Rao, V. R. (1971). Conjoint measurement for quantifying judgmental data. Journal of Marketing research, pages 355–363.
Green, P. E. and Srinivasan, V. (1978). Conjoint analysis in consumer research: issues and outlook. Journal of consumer research, 5(2):103–123.
Hagerty, M. R. (1985). Improving the predictive power of conjoint analysis: The use of factor analysis and cluster analysis. Journal of Marketing Research, pages 168–184.
Halme, M. and Kallio, M. (2014). Likelihood estimation of consumer preferences in choice-based conjoint analysis. European Journal of Operational Research, 239(2):556–564.
Heberlein, T. A. and Baumgartner, R. (1978). Factors affecting response rates to mailed questionnaires: A quantitative analysis of the published literature. American Sociological Review, pages 447–462.
Louviere, J. J. and Woodworth, G. (1983). Design and analysis of simulated consumer choice or allocation experiments: an approach based on aggregate data. Journal of marketing research, pages 350–367.
Malhotra, N. K. (1986). An approach to the measurement of consumer preferences using limited information. Journal of Marketing Research, pages 33–40.
Ogawa, K. (1987). An approach to simultaneous estimation and segmentation in conjoint analysis. Marketing Science, 6(1):66–81.
Orme, B. K. (2010). Getting started with conjoint analysis: strategies for product design and pricing research. Research Publishers.
Pekelman, D. and Sen, S. K. (1979a). Improving prediction in conjoint measurement. Journal of Marketing Research, pages 211–220.
Pekelman, D. and Sen, S. K. (1979b). Measurement and estimation of conjoint utility functions. Journal of Consumer Research, 5(4):263–271.
Rossi, P. E. and Allenby, G. M. (2003). Bayesian statistics and marketing. Marketing Science, 22(3):304–328.
Sichtmann, C. and Wilken, R. (2015). Estimating willingness-to-pay by different utility functions: A comparison of individual and cluster solutions. In Revolution in Marketing: Market Driving Changes, pages 263–268. Springer.
Spiegelhalter, D., Thomas, A., Best, N., and Lunn, D. (2007). Openbugs user manual, version 3.0. 2. MRC Biostatistics Unit, Cambridge.
Sturtz, S., Ligges, U., and Gelman, A. (2010). R2openbugs: a package for running openbugs from r. URL http://cran. rproject.org/web/packages/R2OpenBUGS/vignettes/R2OpenBUGS. pdf.
Voleti, S., Srinivasan, V., and Ghosh, P. (2016). An approach to improve the predictive power of choice-based conjoint analysis. International Journal of Research in Marketing.