[R] Missing values in the nlme package

[ripley@stats.ox.ac.uk]

On Tue, 28 May 2002 laura at bayesian-bay.freeserve.co.uk wrote:

> Hi,
>
> I am using the nlme package to fit random effects models, however, I
> have many missing values in my response variable which I cannot just
> omit.
>
> I can't replace the missing values with the mean or median either as
> this is too simple and would need to use something like imputation or
> the EM Algorithm.
>
> Is there any way of including these missing values since the model will
> not run when they are left as NA.

These are missing _response_ values.  You have not told us why they are
missing.  If they are missing completely at random you may as well omit
the rows altogether.  If missingness is informative, you will need to
model the missingness (and probably use multiple imputation).

-- 
Brian D. Ripley,                  ripley at stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  +44 1865 272861 (self)
1 South Parks Road,                     +44 1865 272860 (secr)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
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
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._