[R-sig-ME] Random vs. fixed effects

Liaw, Andy andy_liaw at merck.com
Fri Apr 23 15:49:44 CEST 2010

I'm by no means expert, but it seems to me that this is more a
philosophical question than a technical one.

To me, a factor is treated a fixed effect if the interest is in the
differences from one level to another (or some contrasts).  A random
factor, on the other hand, is when the interest is in the variability
due to the factor, and the levels of the factor can be considered as a
sample from a (Gaussian) population.  The problem is, if a factor has
only three levels, can we really reliably estimate the variance of the
population from which the three levels of the factor were drawn from?
Well, if you must, you must.  However, it seems to me that if the factor
is really a blocking variable (thus basically nuisance parameters), one
can go either way.

I'd very much welcome the real experts' corrections or comments.


> -----Original Message-----
> From: r-sig-mixed-models-bounces at r-project.org 
> [mailto:r-sig-mixed-models-bounces at r-project.org] On Behalf 
> Of Schultz, Mark R.
> Sent: Friday, April 23, 2010 9:38 AM
> To: r-sig-mixed-models at r-project.org
> Subject: [R-sig-ME] Random vs. fixed effects
> I just read a post by Andrew Dolman suggesting that a factor 
> with only 3
> levels should be treated as a fixed effect. This seems to be 
> a perennial
> question with mixed models. I'd really like to hear opinions from
> several experts as to whether there is a consensus on the topic. It
> really makes me uncomfortable that such an important modeling decision
> is made with an "ad hoc" heuristic.
> Thanks,
> Mark Schultz, Ph.D.
> Bedford VA Hospital
> Bedford, Ma. 
> 	[[alternative HTML version deleted]]
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
Notice:  This e-mail message, together with any attachme...{{dropped:10}}

More information about the R-sig-mixed-models mailing list