R help - Oct 2005 - linear mixed effect model with ordered logit/probit link?

Hello,

I'm working on the multiple categorical data (5-points scale) using linear 
mixed effect model and wondering if anyone knows about or works on the 
linear mixed effect model with ordered logit or probit link.
I found that the "lmer" function in R is very flexible and supports 
various models, but not ordered logit/probit models. I may conduct my 
analysis by turning my DVs into nested dichotonomies, but just wonder if 
there is anyway that I can do this without transforming my DVs. Any help 
or suggestion will be greatly appreciated.

Thanks,

Byoung-Inn



Byoung-Inn Bai
Ph.D. Candidate
University of Washington
Department of Political Science
Box 353530
e-mail: bbi68 at u.washington.edu

Hi friends, I have a question.

I have this piece of my program and how you see, that's ok (whit >
num<-
0.002)

num<-0.002
factor1<-1;
while(1)
{
if (num*factor1<1)
factor1<-factor1*10
else
{
print("out ok!!");
break;
}
}

[1] "out ok!!"


but when I change (whit > num<-0) R show this:

Error in if (num * factor1 < 1) factor1 <- factor1 * 10 else { :
missing value where TRUE/FALSE needed


I can't understand that error, can somebody help, please
thanks
 Jac

	[[alternative HTML version deleted]]

Have you received a reply to this?  I haven't seen one.  I just tried 
several things with RSiteSearch.  Searching for "ordered logit"
produced
70 hits.  One of the first 10 indicate, "The CRAN package MCMCpack has 
at least ordered probit." 
(http://finzi.psych.upenn.edu/R/Rhelp02a/archive/38663.html)

	  I haven't used ordered probits or logits or MCMC, but it would seem 
to me that if MCMCpack has ordered probits, it surely should also be 
able to handle mixed effects.

	  If you would like further assistance from this listserve, I suggest 
you read the posting guide (www.R-project.org/posting-guide.html). 
Doing so might increase the chances of obtaining a useful reply quickly, 
especially if your question includes an extremely simple example in a 
few lines of R code that someone can copy from your email into R and 
test a few ideas in a minute or so.

	  Best Wishes,
	  spencer graves

byoung-inn bai wrote:
> Hello,
> 
> I'm working on the multiple categorical data (5-points scale) using
linear
> mixed effect model and wondering if anyone knows about or works on the 
> linear mixed effect model with ordered logit or probit link.
> I found that the "lmer" function in R is very flexible and
supports
> various models, but not ordered logit/probit models. I may conduct my 
> analysis by turning my DVs into nested dichotonomies, but just wonder if 
> there is anyway that I can do this without transforming my DVs. Any help 
> or suggestion will be greatly appreciated.
> 
> Thanks,
> 
> Byoung-Inn
> 
> 
> 
> Byoung-Inn Bai
> Ph.D. Candidate
> University of Washington
> Department of Political Science
> Box 353530
> e-mail: bbi68 at u.washington.edu
> 
> ______________________________________________
> 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
-- 
Spencer Graves, PhD
Senior Development Engineer
PDF Solutions, Inc.
333 West San Carlos Street Suite 700
San Jose, CA 95110, USA

spencer.graves at pdf.com
www.pdf.com <http://www.pdf.com>
Tel:  408-938-4420
Fax: 408-280-7915