[R] simulating Gaussian Mixture Method

From: Peng Jiang <jp021_at_sjtu.edu.cn>
Date: Mon, 16 Jun 2008 13:48:22 +0800

  Hi,

  I have a mixture pdf which has three components, each satisfies the 6 dimension normal distribution.

   I use mvrnorm() from the MASS library to generate 1000 samples for each component and I add them
  to get the random samples which satisfies with the mixture distribution.

  I use Mclust() from the mclust library to get the model of the samples and strange things happened.
  First it gave a warning

> samplesMclust <- Mclust( samples )

  Warning messages:
1: In summary.mclustBIC(Bic, data, G = G, modelNames = modelNames) :

   best model occurs at the min or max # of components considered 2: In Mclust(samples) : optimal number of clusters occurs at min choice

Then I input
> samplesMclust

  best model: XXI with 1 components

  it says the best model is with 1 component !

   I am confused ... Is it because the way that I generate samples is wrong???

   thanks so much !



Peng Jiang
江鹏
Ph.D. Candidate

Antai College of Economics & Management
安泰经济管理学院
Department of Mathematics
数学系
Shanghai Jiaotong University (Minhang Campus) 800 Dongchuan Road
200240 Shanghai
P. R. China



R-help_at_r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. Received on Mon 16 Jun 2008 - 05:53:01 GMT

Archive maintained by Robert King, hosted by the discipline of statistics at the University of Newcastle, Australia.
Archive generated by hypermail 2.2.0, at Mon 16 Jun 2008 - 06:31:48 GMT.

Mailing list information is available at https://stat.ethz.ch/mailman/listinfo/r-help. Please read the posting guide before posting to the list.

list of date sections of archive