Parameter Estimation for the Four Parameter Beta Distribution.
Abstract
This investigation compared six estimation methods for the parameters of the four parameters Beta distibution. The methods used are the full four-moments estimator, four modified moment estimators, and a modified maximum likelihood estimator. A closed form solution is derived for the full moment estimator which the author has been unable to find in the literature. The four modified moment estimators are each defined by two moment equations and two equations involving the first and last order statistics. The modified maximum likelihood estimate is defined using the skewness and kurtosis indices to define the shape parameters and then solving for the maximum likelihood estimate of the location parameters, when it exists.
Document Details
- Document Type
- Technical Report
- Publication Date
- Dec 01, 1983
- Accession Number
- ADA138062
Entities
People
- B. R. Treat
Organizations
- Air Force Institute of Technology