Re: Bimodal Gamma Distribution


"Ray Koopman" <koopman@xxxxxx> wrote in message
news:b166ec78-ff3d-42f0-9f50-c1060f74e91f@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
On Jul 2, 6:16 am, gundalav <gunda...@xxxxxxxxx> wrote:
Hi all,

Is it true that Gamma distributions "cannot" model
the bimodal distributions?

Is there any literature I can refer to that says
that Gamma distribution is "always" unimodal?

For example I have the following figures.

http://docs.google.com/View?docid=dcvdrfrh_1dk9r2rc7

It has two peaks in the density.

The red line is normal curve and green line is gamma curve.
Notice that red line can correctly fit the histogram that has two
peaks (i.e. red curve also has two peaks).

But the gamma curve there only has one curve.

I was wondering if I can fit the gamma function such that it also
yields two peaks.

Regards,
GV.

Try a mixture of two gammas.

The red line in yourfigure is NOT a Normal distribution.
A Normal distribution, like a gamma distribution, has only one
mode (peak). For on-line "literature" try
http://en.wikipedia.org/wiki/Normal_distribution
http://en.wikipedia.org/wiki/Gamma_distribution
http://www.causascientia.org/math_stat/Dists/Compendium.pdf
and note that the expressions for the modes of the Normal and
the Gamma are single valued. You may find the "Continuous
Mixtures" section of Compendium.pdf interesting, but working
with mixtures of distributions can be awkward.

Hope that helps,

A Lurker


.

Relevant Pages

  • Re: Predicting using SAS-Survival analysis
    ... The problem with simply using the highest likelihood is that those ... one parameter, Weibull, logistic, log-normal, normal, and log-logistic ... are two-parameter distributions, and gamma has three. ... chi-square distribution with 1 degree of freedom, ...
    (sci.stat.math)
  • Re: Predicting using SAS-Survival analysis
    ... The problem with simply using the highest likelihood is that those ... one parameter, Weibull, logistic, log-normal, normal, and log-logistic ... are two-parameter distributions, and gamma has three. ... chi-square distribution with 1 degree of freedom, ...
    (sci.stat.edu)
  • Re: Question about multimodal parameter estimation
    ... distribution plus a normal distribution, in fact the look like this ... in addition to the parameters for the gamma and normal densities. ... This is the beginning of the FLXglm documentation: ... FlexMix Interface to Generalized Linear Models ...
    (sci.stat.math)
  • Bimodal Gamma Distribution
    ... Is it true that Gamma distributions "cannot" model ... It has two peaks in the density. ... The red line is normal curve and green line is gamma curve. ...
    (sci.stat.math)
  • Re: Game Theory Nobel Prize Again and Beyond With PI
    ... mutations based on the Levy probability distribution," by Chang- ... the same distribution under sums goes to the "+" side of the ledger ... Readers who recall that the gamma distribution is ...
    (sci.stat.math)