[R] Gaussian mixture models, modelNames: EEV, VEV mclust2002

Bjoern Egert egert at inf.uni-konstanz.de
Fri Sep 26 14:26:07 CEST 2003


Hello,

I am using the parameterized EM- Algorithm in clustering context.
I use generated datasets, containing 5000 points in 20 dimensions with 5
clusters.
The following poses a problem for me:



   emEst<-me(modelName="EEV",data=data[,1:numDimensions],z=unmap(x))    
   emEst<-me(modelName="VEV",data=data[,1:numDimensions],z=unmap(x))  
   coordProj(main="Model
EEV",data,dimens=c(1,2),type="classification",ask=F,mu=emEst$mu,sigma=em
Est$sigma,z=emEst$z)      
   coordProj(main="Model
EEV",data,dimens=c(1,2),type="classification",ask=F,mu=emEst$mu,sigma=em
Est$sigma,z=emEst$z) 



For these two Models, neither the constraint "E" für equal shape, nor
the constraint "E" for equal Volume seems to have any impact on the
model. In contrast, for all other models, the constraints apply fine...


How is this to be explained ?

Thanks a lot
Best regards
Bjoern




More information about the R-help mailing list