, Volume 21, Issue 1, pp 133–141 | Cite as

On the resolution of a mixture of observations from two gamma distributions by the method of maximum likelihood

  • J. P. Dickinson


The gamma distribution occurs very frequently in applied statistical work. This paper considers in detail the problem of assigning to their population of origin the members of a sample which is the result of mixing two random samples from two distinct gamma populations, and of providing estimates for the parameters (of scale and location) of these two populations.

Some attempts have previously been made to approach this problem using the usual maximum likelihood method, but have met with little success because of the extreme intractibility of the resulting maximum likelihood equations. Recently, a slightly different model has been considered from the maximum likelihood viewpoint in the cases of a mixture of Gaussian distributions, and of gamma distributions. In the later case, however, such severe constraints were placed on the population parameters that effectively only a trivial case was discussed.

This paper develops the range of results available for resolving a mixture of gamma distributions to an extent that covers most situations that are likely to arise in practice.

The final section of the paper considers the asymptotic properties of the estimators briefly in general, and in detail in a particular case.


Gaussian Distribution Random Sample Stochastic Process Probability Theory Economic Theory 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Abramowitz, M., andI. A. Stegun: Handbook of Mathematical Functions, Dover Publications, Inc., New York 1965.Google Scholar
  2. Blischke, W. R.: Estimating the Parameters of Mixtures of Binomial Distributions. Journal of the American Statistical Association,59, 510–528, 1964.Google Scholar
  3. Charlier, C. V. L., andS. D. Wicksell: On the Dissection of Frequency Functions. Arkiv for Mathematik, Astronomi och Fysik, Bd.18, No. 6, 1924.Google Scholar
  4. Cohen, A. C. Jr.: Estimation in Mixtures of Two Poisson Distributions. Aero-Astrodynamics, Research and Development, Research Review No. 1, NASA TM X-53189, 104–107, 1964.Google Scholar
  5. Gregor, J.: An Algorithm for the Decomposition of a Distribution into Gaussian Components. Biometrics,25, 79–93, 1969.Google Scholar
  6. John, S.: On Identifying the Population of Origin of Each Observation in a Mixture of Observations from Two Normal Populations. Technometrics,12, 553–564, 1970a.Google Scholar
  7. —: On Identifying the Population of Origin of Each Observation in a Mixture of Observations from Two Gamma Distributions. Technometrics,12, 565–568, 1970b.Google Scholar
  8. Kao, J. H. K.: A Graphical Estimation of Mixed weibull parameters in Life-Testing of Electron Tubes, Technometrics,1, 389–407, 1959.Google Scholar
  9. Pearson, K.: Contributions to the Mathematical Theory of Evolution, Philosophical Transactions of the Royal Society, A185, 71–110, 1894.Google Scholar
  10. Rider, P. R.: Estimating the parameters of Mixed Potsson. Binomial and Weibull Distributions by the Method of moments. Bulletin of the International Statistical Institute,39, 225–232, 1961 a.Google Scholar
  11. —: The Method of Moments Applied to a Mixture of Two Exponential Distributions. Annals of Mathematical Statistics,32, 143–147, 1961b.Google Scholar
  12. Tallis, G. M., andR. Light: The Use of Fractional Moments for Estimating the Parameters of a Mixed Exponential Distribution. Technometrics,10, 161–175, 1968.Google Scholar

Copyright information

© Physica-Verlag Rudolf Liebing KG 1974

Authors and Affiliations

  • J. P. Dickinson
    • 1
  1. 1.Department of Accounting and FinanceUniversity of Lancaster, Furness CollegeLancasterUK

Personalised recommendations