[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: Cluster/PCA for predicting a binary outcome?

From   "K Jensen" <>
Subject   Re: st: Cluster/PCA for predicting a binary outcome?
Date   Wed, 18 Jul 2007 13:09:16 +0100

Thanks, Paul! This is part way towards what I was hoping to do.
I have a set of variables that more-or-less form groups that tend to
be correlated with each other, but not with the other variables.
I would like to produce more than one linear function a la "discrim"
for each of the groups. Or that would have one linear function that
has high weights on one group, another on the second and so on.
BTW, I am making the groups sound a lot more defined than they are; it
is more of a tendency than anything absolute.
Thankyou again

On 18/07/07, E. Paul Wileyto <> wrote:
You're looking for discriminant analysis (look up Stata help on
discrim)...  It's like PCA, but you can think of it as selecting the
loadings to maximize the F-value if you did a 1-way ANOVA by your class

But, for a binary outcome, many simply use logistic regression.


K Jensen wrote:
> Hi
> I am trying to predict a binary outcome from a set of correlated
> variables.  Rather than using logisitic regression to include the
> variables one-by-one in the model, I was wondering if there was a way
> in Stata of generating sets or functions of the variables?  Maybe
> something similar to PCA, except that you would be trying to explain
> the variation in the binary outcome rather than the whole dataset.
> I hope that this makes some sort of sense!
> Thankyou
> Karin
> *
> *   For searches and help try:
> *
> *
> *

E. Paul Wileyto, Ph.D.
Assistant Professor of Biostatistics
Tobacco Use Research Center
School of Medicine, U. of Pennsylvania
3535 Market Street, Suite 4100
Philadelphia, PA  19104-3309

Fax: 215-746-7140

*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index