[R] From list to variable name

[Gabor Grothendieck]

Using the built in dataset anscombe this regresses y1 on x1 and y3
ignoring the other columns:

lrm(y1 ~., anscombe[c("y1", "x1", "y3")])

or

lrm(y1 ~., anscombe[c(5, 1, 7)])

either of which eliminate having to calculate special purpose
formulas.

Also see the leaps package.

On Tue, Jul 14, 2009 at 10:21 AM, Michelle
Greve<michelle_greve at yahoo.com> wrote:
>
> Hello
> I am trying to run equations with different combinations of explanatory variables. I have managed to figure out how to generate the different combinations, and am trying to set up equations where I use these combinations. And this is where I am getting stuck. I have searched several R websites but with no success.
>
> This is how I generate the different combinations of my explanatory variables and replace the resulting colons with '+':
>> comb<-cbind(attributes(terms(~ pop_1850AD * pop_500AD * pop_0AD * pop_1000AD * pop_1000BC))$term.labels)
>> x<-gsub(":","+",comb)
>
> I think, what I need to do next, is get rid of the inverted commas. So I have tried several things.
> 1. w<-print(x,quote=F) - this prints out the list without inverted commas, but if I then type 'w' again, the inverted commas have remained.
> 2. I have subsequently tried the following loop:
>> y<-vector(mode = "list", length = length(x))
>> for(i in 1:length(x)){
>>   y[[i]]<-as.name(x[i])
>> }
>     This created a vector with e.g.:
>> y[[7]]
> `pop_1850AD+pop_0AD`
>
> So, I tried putting this into the equation I'm building:
>> hh[[7]]<-lrm(as.factor(ap)~y[[7]])
> only to the following fault message:
> Error in model.frame.default(formula = as.factor(ap) ~ y[[1]], na.action = function (frame)  :
>   invalid type (symbol) for variable 'y[[1]]'
>
> Is there anyway I can build these equations without typing them in by hand? I am not sure where I'm going wrong or what other search terms to use on the help list.
> Thank you,
> Michelle
>
>
>
>
>
> ______________________________________________
> R-help at 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.
>