1. Statistically, you probably don't want to do this at all (but
that's another story).
2. Programatically, you probably want to use one of several packages
that do it already rather than trying to reinvent the wheel. A quick
search on rseek.org for "all subsets regression" brought up this:
http:
It's hard to imagine a situation where this makes sense, but of course
you can do it if you want. Perhaps
rhs <- unlist(sapply(1:(ncol(df)-1), function(x)
apply(combn(names(df)[-1], x), 2, paste, collapse = " + ")))
lapply(rhs, function(x) lm(as.formula(paste("y ~", x)), data = df))
--Ista
On Fr
Suppose I have the following data:
y<-rnorm(10)
age<-rnorm(10)
sex<-rbinom(10,1, 0.5)
edu<-round(runif(10, 1, 20))
edu2<-edu^2
df<-data.frame(y,age,sex,edu,edu2)
I want to run a large number of models, for example:
lm(y~age)
lm(y~age+sex)
lm(y~age+sex+edu)
lm(y~age+sex+edu+edu2)
lm(y~sex+edu2)
3 matches
Mail list logo
