[R] Error running LME model

Ben Bolker bbolker at gmail.com
Wed Feb 9 23:33:17 CET 2011


Christina Hemphill <CHEMPHIL <at> hsph.harvard.edu> writes:

> 
> I'm attempting to run an LME model with random intercepts for location and
have received an error message. 
> The model and error message are given below:
> 
> > mixed.distance <- lme (fixed= log(min5inpnc) ~ i93centerline,
random=~1|location, data = nosmokecomp)
> Error in y[revOrder] - Fitted : non-conformable arrays
> 
> I believe that my dataset may have dimensions that are not
> working with the model, but I'm not sure how to
> diagnose the exact problem.  Can someone provide assistance?

  Hard to answer without a reproducible example (it's only
possible to answer questions without such examples when the
errors are very common with very characteristic symptoms -- not
the case here).
   At the very least we need summary() and/or str() of your data.
  sessionInfo() wouldn't hurt either.
   Do you have NAs or negative values in your response variable?
  In general, lme questions should go to the r-sig-mixed-models
mailing list.

  Ben Bolker



More information about the R-help mailing list