Representation of multivariate Bernoulli distributions with a given set of specified moments

JOURNAL OF MULTIVARIATE ANALYSIS

卷:168

Article

Fontana, Roberto¹  Semeraro, Patrizia¹ 

[1] Politecn Torino, Dipartimento Eccellenza 2018 2022, DISMA Dipartimento Sci Matemat Giuseppe Luigi Lag, Turin, Italy

关键词: Algebraic statistics;    Correlation;    Frechet class;    Multivariate binary distribution;    Simulation;   

DOI  :  10.1016/j.jmva.2018.08.003

来源: Elsevier

【 摘 要 】

We propose a simple but new method of characterizing multivariate Bernoulli variables belonging to a given class, i.e., with some specified moments. Within a given class, this characterization allows us to generate easily a sample of mass functions. It also provides the bounds that all the moments must satisfy to be compatible and the possibility to choose the best distribution according to a certain criterion. For the special case of the Frechet class of the multivariate Bernoulli distributions with given margins, we find a polynomial characterization of the class. Our characterization allows us to have bounds for the higher order moments. An algorithm is presented and illustrated. (C) 2018 Elsevier Inc. All rights reserved.

【 授权许可】

Free