[R] Fractional multinomial logit model or similar in R for analysis of behavior?

[David Winsemius]

On Apr 9, 2014, at 10:25 AM, Brian Battaile wrote:

> I'm looking for a method to analyse behavior data that can be assigned to
> multiple categories
> as a proportion with all the categories adding to 1 and some explanatory
> variables and repeated measures on some individuals.

Maybe expanding your search strategy would help. What you are describing sounds like a Dirichlet problem. Consider searching on "dirichlet regression".

I got 325 links in 100 packages with sos::findFn("dirichlet regression"), but it's not my field so you need to judge suitability.


And ... this mailing list requests postings to be plain text.
-- 
David.
> 
> Data would look something like this
> 
> AnimalID Behavior1 Behavior2 Behavior3 Covariate1 Covariate2
> 1 0.75 0.2 0.05 1 0
> 2 0.5 0.25 0.25 0 0
> 2 0.6 0.3 0.1 0 0
> 3 0.7 0.25 0.05 1 1
> ....
> 
> There is a fractional multinomial logit model (fmlogit) in Stata that is
> designed to do this
> analysis ala
> Papke, Leslie E. and Jeffrey M. Wooldridge. 1996.  Econometric Methods for
> Fractional Response Variables with     an Application to 401(k) Plan
> Participation Rates. Journal of Applied Econometrics 11(6):619-632.
> 
> but I have not found anything in R.  If anyone knows of something similar
> in R or perhaps a different approach I would be grateful to hear about it.
> 
> Thank you
> Brian Battaile
> University of British Columbia
> US Geological Survey
> 
> 	[[alternative HTML version deleted]]
> 
> ______________________________________________
> 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.

David Winsemius
Alameda, CA, USA