[R] Mixed models quantile regression

[roger koenker]

There is no generally agreed upon notion of random effects for quantile
regression applications.   Insofar as one is willing to accept the  
idea that
random effects are just "shrunken fixed effects" one can consider  
similar
schemes in the QR context; one such is described in

“Quantile Regression for Longitudinal Data,” J. of Multivariate  
Analysis,
(2004),  91, 74-89.

But there are many open questions,  so this is not for the faint hearted
and there is certainly no "official" code.


url:    www.econ.uiuc.edu/~roger            Roger Koenker
email    rkoenker at uiuc.edu            Department of Economics
vox:     217-333-4558                University of Illinois
fax:       217-244-6678                Champaign, IL 61820


On Feb 5, 2008, at 9:40 PM, Beth Strain wrote:

>
> Dear R,
> I have a question concerning quantile regression models.
>
> I am using the quantile regression model to test the relationship  
> between
> abalone and the percentage cover of algae etc at different sites and  
> depths.
>
> An example is
> fit<-rq(abalone~%coversessileinvertebrates+factor(Depth) 
> +factor(Site),tau=0.7)
>
> In this model depth is fixed and site is random. My question is, is it
> possible specify the fixed and random effects in this model. If so  
> could
> someone please give me an example of how to write the code.
>
> I can;t seem to find any information in the R help.
> Thanks in advance
> Beth Strain
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.