[R] Combine variables of different length
R. Michael Weylandt
michael.weylandt at gmail.com
Tue Nov 1 16:14:51 CET 2011
Perhaps something like this:
X = jitter(1:10)
Y = jitter(3*X-5, factor = 3)
X = NA
m = lm(Y~X)$fitted.values
fits <- rep(NA, length(X)); fits[as.numeric(names(m))] <- m;
On Tue, Nov 1, 2011 at 8:52 AM, Johannes Radinger <JRadinger at gmx.at> wrote:
> I have got a dataset with
> the variables Y,X1,X2,X3.
> Some of these variables contain NAs. Therefore
> incomplete datasets aren't recognized when
> I am doing a regression like:
> model <- lm(Y~X1+X2+X3)
> so the resulting vector of resid(model) is
> obviousely shorter then the original variables.
> How can I combine the residuals-vector with
> the original dataset (Y,Xi,...). I recognize
> that the residuals give also a kind of an index
> like from the row names (2,5,7,8,9,12)...
> Is it possible to use in such a case the
> data.frame command? Or what is the best
> way to attach the resulting residuals back to
> the original dataframe with incomplete datasets?
> R-help at r-project.org mailing list
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
More information about the R-help