[R] Logistic Regression - Results?

[Prof Brian Ripley]

On Wed, 24 May 2006, Wojciech Gryc wrote:

> Hi,
>
> I use SPSS at work and have R installed both at work and on my home machine.
> I've been trying to do some logistic regressions in R and SPSS, but the
> results I'm getting are different. I've followed a few R tutorials, and with
> most of them, I get the following instructions:
>
> result <- glm(z ~ x + y, family=binomial(logit))
>
> In the case above, with three variables (z being dependent).
>
> In SPSS, I'm told to use Analyze -> Regression -> Binary Logistic, where I
> put x, y in "Covariates" and z in "Dependent". Note that my values for x and
> y are either 1 or 0.
>
> The results I get from these two tests are different, however, and I was
> wondering why. Am I choosing the wrong commands? If not, why are the results
> different? Any help would be greatly appreciated, and please note that I
> have a limited amount of stats knowledge.

If you show us an example and both outputs we may be able to help.  `the
results I'm getting are different' covers too many possibilities.

(Please see the posting guide for how to prepare a question like this.)

-- 
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 272866 (PA)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595