Re: st: Cluster Analysis

[Michel Camus <mcamus@videotron.ca>]

Nick Cox wrote:

> Janet Noble wrote:
>  
>
> > I have inherited a dataset consisting of 40 variables 
> > (binary, categorical 
> > and continuous) which may be diagnostic predictors of the 
> > state of a tumour. 
> > I was going to use cluster analysis using Gower's 
> > coefficient of similarity 
> > (Cluster Analysis, Everitt et al) to find which variables 
> > best predict the 
> > tumour state but this does not appear to be implemented in 
> > Stata 8. Is there 
> > any other coefficicient or a completely different analysis 
> > I could use in 
> > Stata. I really do not want to buy another statistical 
> > package but I will if 
> > I have to.
> >    
> Given the clear identification of a response 
> variable, this doesn't sound like a cluster analysis 
> problem at all. Which predictive model(s) is or 
> are appropriate will depend on how tumour state 
> is quantified. 
> Nick 
> n.j.cox@durham.ac.uk 
>  
Janet,
I agree with Nick. What is your rationale for cluster analysis? Where 
would your predicted outcome variable appear in such an analysis? How 
would you maximize the predictive power of your exporatory model?
Usually, cancer staging should be best modelled with ordered logistic 
regression.
Unordered polytomous logistic regression can be used to explore 
peculiarities of individual stages but it will be less parcimonious than 
ordered regression and will tend to "overfit" your sample  for each 
stage with less generalisability to other populations. 
Michel  
~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ 
~ ~ ~ ~ ~

Michel Camus, Ph.D.

�pid�miologue, Div. Biostatistique et �pid�miologie, DGSESC, Sant� Canada

Epidemiologist, Biostatistics and Epidemiology Div., HECSB, Health Canada

Courriel / e-mail : mcamus@videotron.ca <mailto:mcamus@videotron.ca>

T�l�phone / phone     :    (514) 850-0157

T�l�copieur / fax        :    (514) 850-0836

~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ ~ 
~ ~ ~ ~ ~




*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/