Peter Macdonald 

McMaster University

An R Package for Finite Mixture Distributions

We have developed a comprehensive R package for fitting finite mixture distributions to grouped data. The component distributions may be normal, lognormal, gamma, Weibull, binomial, negative binomial, Poisson, beta or Gumbel. The grouped data may have missing or censored bins and may include conditional as well as mixed data. Maximum likelihood estimates are calculated by a combination of EM and quasi-Newton algorithms. Ill-conditioned problems are resolved by constraints on the parameters. Graphical methods include the rootogram as a diagnostic tool. The logic and functionality of the package will be illustrated with examples from different areas of application.