Bayesian estimation of the Bonferroni index from a Pareto-type I population
- Cite this article as:
- Giorgi, G.M. & Crescenzi, M. Statistical Methods & Applications (2001) 10: 41. doi:10.1007/BF02511638
The Bonferroni index (B) is a measure of income and wealth inequality, and it is particularly suitable for poverty studies. Since most income surveys are of a sample nature, we propose Bayes estimators ofB from a Pareto/I population. The Bayesian estimators are obtained assuming a squared error loss function and, as prior distributions, the truncated Erlang density and the translated exponential one. Two different procedures are developed for a censored sample and for income data grouped in classes.