See John Aitchison, 2003, Compositional Data Analysis. -dirifit- implements the Dirichlet model, which is highly restrictive. Otherwise you need to transform the proportions and use a multivariate multiple regression type approach.
Nick Cox has some nice plots from the CDA tradition implemented in Stata, eg., -triplot-.
-----Original Message-----
From: "timothy adler" <[email protected]>
To: [email protected]
Sent: 6/12/2009 7:23 AM
Subject: st: The dependent variable is a multi-proportion in actual values
Hello Stata experts,
Would anyone know of a technique to use when I want to do a regression on a dependent variable which is a multi-proportion?
In particular, I want to estimate the effect of gender on (1) spending on food (2) spending on clothing and (3) spending on recreation.
I cannot use mlogit, because these are actual spending proportions, not categorical values, and I want to estimate them in one regression to know their relationships, like one spending increasing more than the others.
Much appreciated for any help.
Tim
_________________________________________________________________
Looking for a new car this winter? Let us help with car news, reviews and more
http://a.ninemsn.com.au/b.aspx?URL=http%3A%2F%2Fsecure%2Dau%2Eimrworldwide%2Ecom%2Fcgi%2Dbin%2Fa%2Fci%5F450304%2Fet%5F2%2Fcg%5F801459%2Fpi%5F1004813%2Fai%5F859641&_t=762955845&_r=tig_OCT07&_m=EXT
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
