[R] NLME Covariates

Spencer Graves spencer.graves at pdf.com
Mon Mar 27 05:41:16 CEST 2006


	  What you think about the following:

 > set.seed(1)
 > DF0.3 <- data.frame(X=c("a","a", "b"), y=rnorm(3))
 > lme(y~1, random=~1|X, data=DF0.3)
Linear mixed-effects model fit by REML
   Data: DF0.3
   Log-restricted-likelihood: -2.148692
   Fixed: y ~ 1
(Intercept)
  -0.4261464

Random effects:
  Formula: ~1 | X
          (Intercept)  Residual
StdDev: 1.280461e-06 0.5383504

Number of Observations: 3
Number of Groups: 2
 >
	  hope this helps.
	  spencer graves
p.s.  I confess I had difficulties parsing your question.  First, I had 
to Google for "HLM".  I figured it was NOT "Home Life Ministries". 
"Hierarchical Linear Models" seemed more consistent with the context. 
Second, I wasn't even sure about what you meant by "category".  I assume 
it's what is returned by the "levels" function when applied to a "factor".

Robin Martin wrote:

> HLM question?
> 
>  
> 
> Is there a minmum number of observations required for a category..I have
> individusals in work teams.I have incomplete data for all the teams
> ..sometimes I only have data for one person in a team.I assume that HLM
> can't work here!  But what would be the mimimal.at the moment I have a
> sample of about 240 in about 100 teams with teamsizes form 2 to 5.
> 
>  
> 
> Any advice?
> 
>  
> 
> Thanks
> 
>  
> 
> Robin
> 
>  
> 
> _____________________________________________________________
> 
>  
> 
> Dr Robin Martin
> 
> School of Psychology
> 
> University of Queensland
> 
> Brisbane, QLD 4072
> 
> Australia
> 
>  
> 
> Level 1, Room 132, McElwain Bldg
> 
> tel. +61 7 3365 6392
> 
> fax. +61 7 3365 4466
> 
> email r.martin at psy.uq.edu.au
> 
> web-page http://www.psy.uq.edu.au/people/personal.html?id=275
> 
> ______________________________________________
> 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




More information about the R-help mailing list