
A latent class probit model for analyzing pick any/N data
- Author
- Geert De Soete (UGent) and W Desarbo
- Organization
- Abstract
- A latent class probit model is developed in which it is assumed that the binary data of a particular subject follow a finite mixture of multivariate Bernoulli distributions. An EM algorithm for fitting the model is described and a Monte Carlo procedure for testing the number of latent classes that is required for adequately describing the data is discussed. In the final section, an application of the latent class probit model to some intended purchase data for residential telecommunication devices is reported.
- Keywords
- REPRESENTATION, SEGMENTATION, THRESHOLD-MODEL, MAXIMUM-LIKELIHOOD, MARKET SEGMENTATION, MONTE-CARLO SIGNIFICANCE TEST, EM ALGORITHM, FINITE MIXTURE DISTRIBUTION, LATENT CLASS ANALYSIS, PROBIT MODEL
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-227272
- MLA
- De Soete, Geert, and W. Desarbo. “A Latent Class Probit Model for Analyzing Pick Any/N Data.” JOURNAL OF CLASSIFICATION, vol. 8, no. 1, 1991, pp. 45–63.
- APA
- De Soete, G., & Desarbo, W. (1991). A latent class probit model for analyzing pick any/N data. JOURNAL OF CLASSIFICATION, 8(1), 45–63.
- Chicago author-date
- De Soete, Geert, and W Desarbo. 1991. “A Latent Class Probit Model for Analyzing Pick Any/N Data.” JOURNAL OF CLASSIFICATION 8 (1): 45–63.
- Chicago author-date (all authors)
- De Soete, Geert, and W Desarbo. 1991. “A Latent Class Probit Model for Analyzing Pick Any/N Data.” JOURNAL OF CLASSIFICATION 8 (1): 45–63.
- Vancouver
- 1.De Soete G, Desarbo W. A latent class probit model for analyzing pick any/N data. JOURNAL OF CLASSIFICATION. 1991;8(1):45–63.
- IEEE
- [1]G. De Soete and W. Desarbo, “A latent class probit model for analyzing pick any/N data,” JOURNAL OF CLASSIFICATION, vol. 8, no. 1, pp. 45–63, 1991.
@article{227272, abstract = {{A latent class probit model is developed in which it is assumed that the binary data of a particular subject follow a finite mixture of multivariate Bernoulli distributions. An EM algorithm for fitting the model is described and a Monte Carlo procedure for testing the number of latent classes that is required for adequately describing the data is discussed. In the final section, an application of the latent class probit model to some intended purchase data for residential telecommunication devices is reported.}}, author = {{De Soete, Geert and Desarbo, W}}, issn = {{0176-4268}}, journal = {{JOURNAL OF CLASSIFICATION}}, keywords = {{REPRESENTATION,SEGMENTATION,THRESHOLD-MODEL,MAXIMUM-LIKELIHOOD,MARKET SEGMENTATION,MONTE-CARLO SIGNIFICANCE TEST,EM ALGORITHM,FINITE MIXTURE DISTRIBUTION,LATENT CLASS ANALYSIS,PROBIT MODEL}}, language = {{eng}}, number = {{1}}, pages = {{45--63}}, title = {{A latent class probit model for analyzing pick any/N data}}, volume = {{8}}, year = {{1991}}, }