[R] Logistic Regression woes

[Prof Brian D Ripley]

On Tue, 26 Feb 2002, Clayton Springer wrote:

> Hi All,
>
> When I tried to do logistic regression and I got the following messages:
>
> >  SampledW.glm.ALL <- glm (V1 ~ ., family = binomial, data = SampledW)
> Warning messages:
> 1: Algorithm did not converge in: (if (is.empty.model(mt)) glm.fit.null else glm.fit)(x = X, y = Y,
> 2: fitted probabilities numerically 0 or 1 occurred in: (if (is.empty.model(mt)) glm.fit.null else glm.fit)(x = X, y = Y,
>
> The dataset in question has 2 classes and 80 features, and there are a few features which are collinear.
>
> What could my source of trouble here?

I suspect the two groups are linearly separable.  Then there is no
MLE.  How many data points?  Linear separation is common by change for up
to 2p (here 162) data points.

-- 
Brian D. Ripley,                  ripley at stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  +44 1865 272861 (self)
1 South Parks Road,                     +44 1865 272860 (secr)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._