On Nov 13, 2012, at 6:06 PM, SASandRlearn wrote:
> I have over 300 variables in my table. I want to choose only a handful of
> those variables to run through many procedures. Lm(), glm() etc..i have over
> 10 procedures that i need to run those variables everytime. Those handful of
> variables can change everytime if output is satisfactory or not.
How do you represent those variables? Are they only going to appear on the RHS
of hte formula? If the LHS of the formula, say 'outcome', will remain the same
and the variable names can be presented in a character vector drawn from a
list, combvecs, you could do something like this:
reslist <- list()
for (vec in combvecs) {
res1 <- lm(outcome ~ . , data=dat_table[ , c("outcome", vec) ]
res2 <- glm(outcome ~ . , data=dat_table[ , c("outcome", vec) ]
reslist <-c( reslist, list(res1, res2) )
You really should be offering test cases that resemble the structure of your
problem.
>
> I have done this in SAS. Now i need to know how to do this in R. Any help or
> even if someone can point to a previous thread will help.
There are many threads that demonstrate how to use the formula() and
as.formula() functions. The Posting Guide gives pointers on searching the
Archives. You should also note that Nabble is not Rhelp and that your continued
failure to include context will probably result in longer waits for replies
than you might experience.
--
David Winsemius, MD
Alameda, CA, USA
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
