Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: compare propensity to consume
From
"Khieu, Hinh" <[email protected]>
To
"[email protected]" <[email protected]>
Subject
st: compare propensity to consume
Date
Fri, 11 Mar 2011 18:44:01 -0600
Dear statalist members,
I want to compare the propensity to consume 2 products, A and B. across two groups of users. I came up with this model.
Y = (0,1), where 0 if change in Y from t to t+1 increases or equals zero, and 1 if change in Y decreases.
Then, run probit of:
Group1: [Poor group]
Y = f(product A, product B, other control variables)
Group2: [Rich group]
Y = f(product A, product B, other control variables). The model is exactly the same as group1.
What I want to compare:
Is the probability of A being consumed greater than that of B within Group 1?
Is the probability of A being consumed greater than that of B within Group 2?
Is the probability of A being consumed greater than that of A between Groups 1 and 2?
Is the probability of B being consumed greater than that of B between Groups 1 and 2?
Is the probability of A being consumed greater than that of B between Groups 1 and 2?
My questions:
Does my probit setup above allow me to answer the five questions above.
Does someone have a better suggestion for the specification to more easily answer the five questions of interest?
Is there a built-in Stata function to run AND compare the regression coefficients for groups 1 and 2? I don't know any code to run this regression.
I would appreciate any amount of help. Many thanks in advance.
Regards,
Hinh
*
* 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/