This is, more often that not, statistically speaking a bad idea:
you're likely to get a false positive (https://xkcd.com/882/)
But it sounds like something along these lines should work for you to
get the models :
x <- data.frame(rnorm(50), rnorm(50), rnorm(50), rnorm(50))
m <- vector("list", ncol(x)) # Make a list to hold all the resulting models
for(i in seq_along(x)) m[[i]] <- lm(as.formula(paste(names(x)[i],
"~.")), data = x)
To parse that, loop over the columns of x (that's what seq_along will
give you if x is a data frame) -- take the i-th name and model is
based on everything else ("~.") -- coerce that thing to a formula and
pass it to lm() to do the linear model.
Hope this helps,
Michael
On Sat, Apr 7, 2012 at 11:27 AM, kebrab67 <selamgetac...@gmail.com> wrote:
> I have a 11*1562 set of data. I want to regress using ols all combination of
> the ten variables on the eleventh. Store the results of the t test of each
> regression and the r2 to compare which combination is better. the
> combination can use any amount o variables. How can I do that in R?
>
> --
> View this message in context:
> http://r.789695.n4.nabble.com/R-help-tp4539571p4539571.html
> Sent from the R help mailing list archive at Nabble.com.
> [[alternative HTML version deleted]]
>
> ______________________________________________
> 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.
______________________________________________
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.
