×

General properties and estimation of conditional Bernoulli models. (English) Zbl 0969.62038

Summary: Conditional Bernoulli (in short “CB”) models have been recently applied to many statistical fields including survey sampling, logistic regression, case-control studies, lottery, signal processing and Poisson-binomial distributions. We present several general properties of CB models that are necessary for the applications above. We also show the existence and uniqueness of MLE of parameters in CB models and give two efficient algorithms for computing the MLE.
General properties of CB models include: (1) mappings between three characterizations of CB models are homeomorphisms modulo rescaling and order-preserving; (2) CB variables are unconditionally independent and conditionally negatively correlated; (3) a simple formula relating inclusion probabilities of adjacent orders can be used to ease computational burden and provide important implications on odds-ratios.
Asymptotic properties of CB models are also examined. We show that under a mild condition, (1) CB variables are asymptotically independent; (2) covariances of CB variables are asymptotically on a smaller scale than variances of CB variables; and (3) a CB model can be approximated by a multinomial distribution with the same coverage probabilities. The use and implications of each property are illustrated with related statistical applications.

MSC:

62H05 Characterization and structure theory for multivariate probability distributions; copulas
62H12 Estimation in multivariate analysis
62E20 Asymptotic distribution theory in statistics
62E10 Characterization and structure theory of statistical distributions
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Bickel, P. J.; Doksum, K. A., Mathematical Statistics: Basic Ideas and Selected Topics (1977), Holden-Day · Zbl 0403.62001
[2] Chen, S. X., Technical report (1992)
[3] Chen, S. X., Weighted polynomial models and weighted sampling schemes for finite population, Ann. Statist., 26, 1894-1915 (1998) · Zbl 0930.62006
[4] Chen, S. X.; Dempster, A. P.; Liu, J. S., Weighted finite population sampling to maximizing entropy, Biometrika, 81, 457-469 (1994) · Zbl 0816.62008
[5] Chen, S. X.; Liu, J. S., Statistical applications of the Poisson-Binomial and conditional Bernoulli distributions, Statist. Sinica, 7, 875-892 (1997) · Zbl 1067.62511
[6] Chen, S. X.; Melnick, E. L.; Tenenbein, A., Allocating via Sampling—With Application to Credit Rating of Loan Portfolios. Allocating via Sampling—With Application to Credit Rating of Loan Portfolios, Working paper (1998), New York UniversityDepartment of Statistics & OR
[7] Cover, T. M.; Thomas, J. A., Elements of Information Theory (1991), Wiley · Zbl 0762.94001
[8] Csiszár, I., Sanov property, generalized I-projection and a conditional limit theorem, Ann. Probab., 12, 768-793 (1984) · Zbl 0544.60011
[9] Darroch, J. N.; Ratcliff, D., Generalized iterative scaling for log-linear models, Ann. Math. Statist., 43, 1470-1480 (1972) · Zbl 0251.62020
[10] Hanif, M.; Brewer, K. R.W, Sampling with unequal probabilities without replacement: A review, Int. Statist. Rev., 48, 317-335 (1980) · Zbl 0459.62007
[11] Joe, H., A winning strategy for lotto games?, Canad. J. Statist., 18, 233-244 (1990)
[12] Stern, H.; Cover, T. M., Maximum entropy and the lottery, J. Amer. Statist. Assoc., 84, 980-985 (1989)
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.