st: ivreg vs. reg3

[PATGIRI Rajdeep <Rajdeep.PATGIRI@insead.edu>]

Title: Message

Hi,

 

I have a system of two equations, which I have been trying to estimate both through equation-by-equation "ivreg" and also 3-SLS using "reg3".  However, the point-estmates in the two procedures seem to differ a lot.  Crucially, the co-efficients of the instruments used in ivreg becomes all insignificant in reg3.  Can anybody shade some light on why is it happening this way.  For IV procedure, I used both ivreg and ivreg2 with GMM option.

 

Also, is there a way to calculate the Hansen J-statistic for overidentifying restrictions with reg3?

 

Thanks in advance!

 

--------------------------------------------------------------------------------------------
Rajdeep PATGIRI
INSEAD, PhD Student
Boulevard de Constance
77305 Fontainebleau, France

 

Phone:  +33 (0)1 60 72 92 29
Fax:  +33 (0)1 60 74 55 00
Email:  Rajdeep.PATGIRI@insead.edu
Web:  http://www.insead.edu/phd/careers/rpatgiri/index.htm
--------------------------------------------------------------------------------------------