R help - Mar 2006 - How do I report coefficients of categorical fixed effects in a publication?

To whom it may concern:
   
  I recently used lmer (for non-normally distributed data and mixed effects,
using the Laplace method).  All 3 of my fixed effects were categorical,
including two ordered factors and one unordered factor.  In my tables, I
currently report the number of observations for the response variable, and both
the degrees of freedom and Chi Square values from tests of reduced models
against the full model.
   
  However, I would also like to include some indication of the magnitude and
direction of the change in each fixed effect (and interaction effects) as a
function of the response variable.  Is this done with the "estimate +/-
SE" of fixed effects in the summary of the fitted model?  Either way, I am
confused with how to report these effects succinctly, especially because for
categorical variables, each category has its own estimated effect.  What is a
reasonable way to do this?  Or should I just avoid it entirely?
   
  I really appreciate your time and help.  Please reply to
tracysfeldman@yahoo.com or tsfeldman@noble.org
   
  Sincerely,
  Tracy S. Feldman

		
---------------------------------

	[[alternative HTML version deleted]]

Have you read Pinheiro and Bates (2000) Mixed-Effects Models in S and 
S-Plus (Springer)?  The figures and tables in this book should give you 
some ideas that you can adapt to summarizing the results of fits to 
nonnormal data.

	  If you've tried this and still have questions for this listserve, 
PLEASE do read the posting guide!
"www.R-project.org/posting-guide.html"
then submit another post after trying some of the things suggested in 
the posting guide.  In particular, if your question includes a 
self-contained example that someone can copy from your email into R and 
try a few things in less than 60 seconds, I believe you will increase 
your chances of getting useful replies quickly.

	  hope this helps,
	  spencer graves	

Tracy Feldman wrote:
> To whom it may concern:
>    
>   I recently used lmer (for non-normally distributed data and mixed
effects, using the Laplace method).  All 3 of my fixed effects were categorical,
including two ordered factors and one unordered factor.  In my tables, I
currently report the number of observations for the response variable, and both
the degrees of freedom and Chi Square values from tests of reduced models
against the full model.
>    
>   However, I would also like to include some indication of the magnitude
and direction of the change in each fixed effect (and interaction effects) as a
function of the response variable.  Is this done with the "estimate +/-
SE" of fixed effects in the summary of the fitted model?  Either way, I am
confused with how to report these effects succinctly, especially because for
categorical variables, each category has its own estimated effect.  What is a
reasonable way to do this?  Or should I just avoid it entirely?
>    
>   I really appreciate your time and help.  Please reply to tracysfeldman at
yahoo.com or tsfeldman at noble.org
>    
>   Sincerely,
>   Tracy S. Feldman
> 
> 		
> ---------------------------------
> 
> 	[[alternative HTML version deleted]]
> 
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide!
http://www.R-project.org/posting-guide.html