There are two ways to estimate a heckman model: two step vs ML.
For ML, estimates of rho and sigma are reported but not for two step.
Is sigma an estimate of the variance of the error term in the response equation (without inverse mills ratio)? How is it different from SE of regression?
Thanks,
Search found 6 matches
- Mon Aug 25, 2014 8:37 am
- Forum: Econometric Discussions
- Topic: Heckman estimation
- Replies: 2
- Views: 4950
- Fri Jun 07, 2013 7:00 am
- Forum: Programming
- Topic: bds test
- Replies: 4
- Views: 4829
Re: bds test
Thanks, but is there any way to save the bootstrapped p value?
- Thu Jun 06, 2013 1:58 pm
- Forum: Programming
- Topic: bds test
- Replies: 4
- Views: 4829
bds test
First, in the manual book, the series views should be "bdstest(options)" instead of "bds(options)". Second, is there any way to save the bootstrapped p value? Third, how to hide the test result window? For example, I use a loop to do the test for N series and would not like the N...
- Thu Jan 31, 2013 12:07 pm
- Forum: Programming
- Topic: loop and time series control
- Replies: 4
- Views: 4661
Re: loop and time series control
Thank you very much!
- Thu Jan 31, 2013 11:41 am
- Forum: Programming
- Topic: loop and time series control
- Replies: 4
- Views: 4661
Re: loop and time series control
I'm using eviews 7.2
- Thu Jan 31, 2013 11:29 am
- Forum: Programming
- Topic: loop and time series control
- Replies: 4
- Views: 4661
loop and time series control
A very simple, intuitive conversion from returns to index levels Quarterly data runs from 1987Q1 to 2011Q4 program shown as below ************************************************************************************************************************** series level for !i=1 to 100 if !i=1 then level...
