ELICITATION METHODS FOR BETA PRIOR DISTRIBUTION

Main Article Content

Fernado Antônio MOALA
Débora Luzia PENHA

Abstract

A distinctive feature of Bayesian inference is that allows us to use the the expert's information in a statistical analysis. Therefore, the development of methods for construction of prior distributions that represent this information in an appropriate manner is very important for the application of Bayesian inferences. However, the diculty to build a procedure to quantify this prior information has contributed to the development of several procedures for obtaining prior distributions. Then a study to verify how informative these procedures are is of great practical interest. In this paper, the methods proposed by O'Hagan (1998), Fox (1966), Gross (1971) and Bisection to elicit the prior distribution Beta are discussed. A real example is presented to show the application of these methods in a practical situation.

Article Details

How to Cite
MOALA, F. A., & PENHA, D. L. (2016). ELICITATION METHODS FOR BETA PRIOR DISTRIBUTION. Brazilian Journal of Biometrics, 34(1), 49–62. Retrieved from https://biometria.ufla.br/index.php/BBJ/article/view/91
Section
Articles