British Journal of Mathematics & Computer Science, ISSN: 2231-0851,Vol.: 16, Issue.: 3
Beta Likelihood Estimation and Its Application to Specify Prior Probabilities in Bayesian Network
Loc Nguyen1* 1Sunflower Soft Company, Ho Chi Minh City, Vietnam.
1Sunflower Soft Company, Ho Chi Minh City, Vietnam.
(1) H. M. Srivastava, Department of Mathematics and Statistics, University of Victoria, Canada.
(2) Paul Bracken, Department of Mathematics, The University of Texas-Pan American Edinburg, TX 78539, USA.
(1) Radosław Jedynak, Kazimierz Pulaski University of Technology and Humanities, Poland.
(2) Anonymous, USA.
(3) S. Zimeras, University of the Aegean, Greece.
Complete Peer review History: http://sciencedomain.org/review-history/14364
Maximum likelihood estimation (MLE) is a popular technique of statistical parameter estimation. When random variable conforms beta distribution, the research focuses on applying MLE into beta density function. This method is called beta likelihood estimation, which results out useful estimation equations. It is easy to calculate statistical estimates based on these equations in case that parameters of beta distribution are positive integer numbers. Essentially, the method takes advantages of interesting features of functions gamma, digamma, and trigamma. An application of beta likelihood estimation is to specify prior probabilities in Bayesian network.
Maximum likelihood estimation; beta distribution; beta likelihood estimation; gamma function.
Full Article - PDF Page 1-21
DOI : 10.9734/BJMCS/2016/25731Review History Comments