I'm trying to study the relationship between two
variables Y1 and Y2.While both variables are
'continuous' taking on values between 0 and 1,
conceptually there is a difference between 0 values
and >0 values.
My theory suggests that firms will begin by choosing
either Y1 or Y2. Once they choose Y1 their probability
of choosing Y2 monotonically decreases as Y1
increases. Beyond a point however, as Y1 increases the
probability of choosing Y2 increases.The reverse holds
true if they initially choose Y2.
I would now like to formally test this using Stata.
I basically would like to show that after controlling
for various firm characteristics, once Y1 is selected,
the probability of Y2 being selected has a U shaped
relationship with Y1 and vice versa. I dont think
'cdsimeq' is applicable. Any other suggestions on how
to deal with this problem would be appreciated.Thank
you!
__________________________________________________
Do You Yahoo!?
Tired of spam? Yahoo! Mail has the best spam protection around
http://mail.yahoo.com
*
* 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/
