×

Predicting multinomial choices using maximum entropy. (English) Zbl 1063.62511

Summary: We discuss two methods for predicting outcomes using the discrete choice generalized maximum entropy (GME) estimator. Since the traditional GME formulation allows \(\widehat{y}\) outside the \([0, 1]\) interval, we specify a new GME formulation, which requires \(0\leq\widehat y\leq 1.\) We estimate a binary choice model to compare results between our GME estimator and the traditional GME estimator.

MSC:

62B10 Statistical aspects of information-theoretic topics
62F10 Point estimation
62J12 Generalized linear models (logistic models)
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Adkins, L., A monte carlo study of a generalized maximum entropy estimator of the binary choice model, (Fomby, T. B.; Hill, R. C., Advances in Econometrics, 12 (1997), JAI Press: JAI Press Greenwich, CT), 189-197
[2] Denzau, A. T.; Gibbons, P. C.; Greenberg, E., Bayesian estimation of proportions with a cross-entropy prior, Communications in Statistics, Part A - Theory and Methods, 18, 1843-1861 (1989) · Zbl 0696.62151
[3] Dhillon, U. S.; Shilling, J. D.; Sirmans, C. F., Choosing between fixed and adjustable rate mortgages, Journal of Money, Credit and Banking, 19, 260-267 (1987)
[4] Golan, A.; Judge, G.; Perloff, J. M., A maximum entropy approach to recovering information from multinomial response data, Journal of the American Statistical Association, 91, 841-853 (1996) · Zbl 0869.62009
[5] Jaynes, E. T., Information theory and statistical mechanics, Physical Review, 106, 620-630 (1957) · Zbl 0084.43701
[6] Jaynes, E. T., Information theory and statistical mechanics II, Physical Review, 108, 171-190 (1957) · Zbl 0084.43701
[7] Judge, G., 1991. A reformulation of ill-posed inverse problems with noise. Unpublished manuscript, University of California, Berkely.; Judge, G., 1991. A reformulation of ill-posed inverse problems with noise. Unpublished manuscript, University of California, Berkely.
[8] Judge, G., Golan, A., Miller, D., 1993. Recovering information in the case of ill-posed inverse problems with noise. Unpublished manuscript, University of California, Berkeley.; Judge, G., Golan, A., Miller, D., 1993. Recovering information in the case of ill-posed inverse problems with noise. Unpublished manuscript, University of California, Berkeley.
[9] Soofi, E. S., A generalizable formulation of conditional logit with diagnostics, Journal of the American Statistical Association, 87, 812-816 (1992)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.