[R] constructing a formula

John Fox jfox at mcmaster.ca
Tue Aug 6 02:55:56 CEST 2002

Dear Mitchell,

At 05:52 PM 8/5/2002 -0400, Michaell Taylor wrote:
>Dear Listers,
>I am having trouble figuring out how to build a formula using a variable
>list.  For example, I have:
>a _ data.frame(a=rnorm(1000))
>and I estimate,
>lm(d ~ b+c+d)

Did you really mean to regress d on predictors including d? (Note that the 
data frame a shadows a$a.)

>I wish to construct a generalized solution in which,
>ListOfVar _ c('b','c','d')
>The question is how to leverage ListOfVar into the constuction of the
>formula lm(a$d ~ a$b+a$c+a$b).  I know this must be fairly simple, but
>unfortunately my readings of the various help files/books haven't been
>productive yet.

Note that a$b appears twice on the RHS of the formula -- probably not what 
you meant.

>Any help would be appreciated.  Thanks in advance.

If all of the variables on the RHS are numeric, as here, then something like
         lm(a$a ~ as.matrix(a[,ListOfVar]))
should work, where a is the data frame containing the variables in the list 
(actually a character vector).

If there are also factors on the RHS of the formula, then you could do 
something like
         lm(eval(parse(text=paste('a ~', paste(ListOfVar, collapse="+")))), 
though someone will probably think of something simpler.

Does that do what you need?

John Fox
Department of Sociology
McMaster University
Hamilton, Ontario, Canada L8S 4M4
email: jfox at mcmaster.ca
phone: 905-525-9140x23604
web: www.socsci.mcmaster.ca/jfox

r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch

More information about the R-help mailing list