Hi Stata-folks,
I was wondering if you could help me with the following problem:
Let y_it be the value of my regressor in state i at time t and X_it be
my regressors. I wish to estimate the model:
y_it = a_i + b_i X_it + e_it
subject to the constraint b_i/a_i = b_j/a_j.
That is, I'd like to run a seemingly unrelated regression system while
restricting the ratio of the slopes to be the same across all states.
I can get the code (attached below, implemented with cnsreg not sureg
for now) to run for a simpler constraint (ie. a_i = a_j), but when I
run it with my more complex constraint I get the following error: "not
possible with test".
Thank you very much!
Erez
Graduate School of Business
University of Chicago
---------------------------------------------------------
* Generating Costraints:
forvalues state_id = 2/51{
local cns_num = 1000 + `state_id'
constraint define `cns_num' aa_PR_`state_id' = (aa_PR_1 / PR_1) * PR_`state_id'
}
* Regressing:
cnsreg R_diff PR_* aa_PR_*, noconstant constraint(1002-1051)
*
* 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/
