Dear all,
I am a stata user and I am moving my first steps in R.
I am dealing with a silly issue concerning looping over variables. I read
previous posts on similar topics in the R help archive, but I did not find a
solution.
Here is my case:
I run a simple bivariate linear regression saving the output in objects
called: pd.memb.0, pd.memb.1, pd.memb.2, pd.memb.3
pd.memb.0 <- lm(E.fs.memb ~ M.fs.memb, data, subset = (tag2 == 1))
pd.memb.1 <- lm(E.fs.memb ~ M.fs.memb, data, subset = (M.fs.memb <=
quantile(M.fs.memb, .25) & tag2 == 1))
pd.memb.2 <- lm(E.fs.memb ~ M.fs.memb, data, subset = (M.fs.memb >
quantile(M.fs.memb, .25) & M.fs.memb <= quantile(M.fs.memb, .75) & tag2 ==
1))
pd.memb.3 <- lm(E.fs.memb ~ M.fs.memb, data, subset = (M.fs.memb >
quantile(M.fs.memb, .75) & tag2 == 1))
Subsequently, I wish to plot my data superimposing a different line for each
regression model. Here I am trying to apply my loop. Looking at the info I
found around, the following code sound to me as correct, but I am wrong.
plot(M.fs.memb , E.fs.memb)
for(i = 1:3){
curve(coef(pd.memb.i)[1] + coef(pd.memb.i)[2]*x, add = T, cex = 100, col =
"red")
}
The plot is plotted, but the curves are not printed and I get the following
error message:
Error in coef(pd.memb.i) :
error in evaluating the argument 'object' in selecting a method for
function 'coef'> }Error: unexpected '}' in "}"
What am I doing wrong?
Thanks a lot for your help,
f.
[[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.
