Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: Interval regression with selection


From   "Bernini, Michele" <Michele.Bernini@unitn.it>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   st: Interval regression with selection
Date   Sun, 26 Feb 2012 10:04:15 +0100

Dear Statalisters,


my dependent variable is collateral as % of loan value reported by firms in BEEPS surveys. Although this variable should be continuous the data are mostly concentrated around "round" values. I interpreted the problem as a case of measurement error in the dependent variable and I suspect that the error is not independent from the value of the variable (it should be smaller in proximity of "round" values). 
To deal with this problem I created intervals of 10 points each and run an interval regression on each lower and upper bound around the reported value. Now I have 45 intervals and some of them are empty.
I first estimated the model including the 0s in the estimation but now I would like to check my results with a selection model. Could you please tell me if you think it is possible to include the Inverse Mills Ratio from the Probit model ( collateral yes/no) within the Interval regression model and if you think that interval regression is the right strategy to deal with measurement error.

Thanks in advance for your suggestions.



Michele Bernini
Phd Candidate
School of International Studies (SIS)
University of Trento
Via Verdi, 8/10 
I-38122 Trento 
Italy

Tel. +39 3491831687





*
*   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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index