st: interpreting interaction term in mtlogit

["stata_user stata_user" <stata_dofile@hotmail.co.uk>]

Hi,
I have an outcome variable �y� with 4 categories and tow independent 
variables
�x1�, sex (male (coded 0)  and female (coded 1))
and �x2�, age (continuous)

I consider the following model
xi: mlogit y  i.x1*x2, baseoutcome(1) rrr

I got rrr parameters (equivalent to odds ratios) for each of the three 
values of y (y2,y3,y4)

I consider y1 as refrence

The rrr are for  (y2 vs y1)

Sex= 1 (female) : b1
Age : b2
And for age*sex:  b3

I interpret the rrr as follows


For (the parameter of sex) the likelihood of being in y2 vs y1 for female 
compared to male, for fixed age is b1

For (the parameter of age) each year increases, gives a likelihood of b2 of 
being in y2 vs y1 among males

And
For (the parameter of age*sex) each year increases, gives a likelihood of b2 
of being in y2 vs y1 among females

Thanks a lot for any comments

Sami

_________________________________________________________________
Windows Live� Messenger has arrived. Click here to download it for free! 
http://imagine-msn.com/messenger/launch80/?locale=en-gb

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/