Estimation of the GLD paramaters for grouped data
 

Summary
In this paper we consider the problem of fitting a five-parameter generalization of the Lambda distribution to data given in the form of a grouped frequency table. The estimation of parameters is done by six different procedures: percentiles, moments, probability-weighted moments, minimum Cramér-Von Mises, maximum likelihood, and pseudo least squares. These methods are evaluated and compared using a Monte Carlo study where the parent populations were GLD approximations of Normal, Beta, Gamma random variables and for nine combinations of sample sizes and number of classes. Of the estimators analyzed is concluded that, although the method of pseudo least squares suffers from a number of limitations, it appears to be the candidate procedure to estimate the parameters of a GLD from grouped data.

keywords
Distribution fitting, quantile function, goodness of fit

Communications in Statistics - Theory and Methods Vol. 34, 1689-1709 (2005)

Back to main publications	Home page	Adobe pdf