On 25-Mar-2002 Peter Dalgaard BSA wrote:Fredrik Karlsson <

fredrik.karlsson@ling.umu.se> writes:

Hi all!

I want to do some logistic regression. Is there a fintion in R that does

this, or do I have to do the variable conversion by hand?

Thankful for all the help I can get.

glm(...., family=binomial) should do it (unless you mean something

different than the usual by "logistic regression")

glm() gives results in terms of log odds ratios. Most epidemiologists

that I know prefer to think in terms of odds ratios, and it would be

quite helpful to have a summary function that reports estimates and

confidence intervals for the transformed parameters. I don't know if

that is what Fredrik means by "variable conversion", but it reminded me of

this problem. I suggest a "transform=FUN" argument for summary.glm.

Incidentally, stata and SAS both have separate procedures for logistic

regression and glms, perhaps for this reason, in addition to historical

ones.

Martyn

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-

r-help mailing list -- Read

http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.htmlSend "info", "help", or "[un]subscribe"

(in the "body", not the subject !) To: r-help-request at stat.math.ethz.ch

_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._