@ Copyright 2005, Jeff Miller.
This program and its documentation may be duplicated and used without charge for any educational or noncommercial purposes. For commercial use, please contact the author.
FitDist is a general-purpose program to fit probability distributions to sets of observed data values. It can be used for answering such questions as ``Are my data better fit by a normal distribution or a gamma distribution?'' or ``Are my data consistent with the assumption of a lognormal distribution?'' or ``What are the best-fitting logistic distribution parameter values for my data set?''
FitDist can fit more than 30 statistical distributions, including the normal, uniform, gamma, exponential, lognormal, logistic, Wald, Weibull, binomial, geometric, etc. It can also fit distributions derived from these by convolution, mixturing, censoring, order statistics, etc. The user provides the observed data, and the program provides the best-fitting parameter estimates for the user-selected distributions. The program runs in a cmd window, with input from text files and output to text files.
FitDist can fit distributions (i.e., estimate their parameters) either by maximizing the likelihood of a set of data points, by minimizing the chi-square of observed versus predicted frequencies in data bins, by trying to match a set of observed moments of the data set (i.e., mean, variance, etc), or by trying to match certain observed percentiles.