A New Test of Attribute Significance for Nonparametric Conjoint Models
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
A new chi-square test is proposed to assess significance of attributes for nonparametric conjoint models. The key idea is to form subsets of rankings and test the dependence between the attribute levels and the sets of rankings. The null hypothesis states that the rankings for profiles with the focal attribute are distributed randomly among the sets of rankings. The approach is simple, easy to use, and can be applied at the individual level as well as at the aggregate level. It can be used for the trade-off approach as well as for the full profile approach.
Abstract
A new chi-square test is proposed to assess significance of attributes for nonparametric conjoint models. The key idea is to form subsets of rankings and test the dependence between the attribute levels and the sets of rankings. The null hypothesis states that the rankings for profiles with the focal attribute are distributed randomly among the sets of rankings. The approach is simple, easy to use, and can be applied at the individual level as well as at the aggregate level. It can be used for the trade-off approach as well as for the full profile approach.
참고문헌 (10)
- Cattin, "Com- mercial Use of Conjoint Analysis Journal of Marketing", pp.44~53 (1982)
- Friedman, "The Use of Ranks to Avoid the Assumption of Normality Implicit in the Analysis of Variance Journal of the American Statistical Association", pp.675~701 (1937)
- Green, "Conjoint Analysis in Consumer Research Journal of Consumer Research", pp.103~123 (1978)
- Green, "Conjoint Analysis in Marketing New Developments with Implications for Research and Practice Journal of Marketing", pp.3~19 (1990)
- Johnson, "Trade-off Analysis of Consumer Values Journal of Marketing Research", pp.121~127 (1974)
- Kivetz, R, "Alternative Models for Capturing the Compromise Effect", 41(8), pp.237~257 (2004)
- Kohli, "Assessing Attribute Significance in Conjoint Analysis Journal of Marketing Research", (nparametric tests and empirical validation), pp.123~133 (1988)
- W. H, "Use of Ranks on One Criterion Variance Analysis Journal of the American Statistical Association", pp.583~621 (1952)
- Louviere, J. J, "Stated Choice Methods: Analysis and Application" (2000), New York: Cambridge University Press
- D. R, "Com- mercial Use of Conjoint Analysis Journal of Marketing", pp.91~96 (1989)