Hi, Listers
I am puzzled that the IVREG and 2sls give out the following different
results:
. qui reg l_tobinq csk cash so1_cf nta
. predict l_tobinq_hat
(option xb assumed; fitted values)
. reg invest l_tobinq_hat cash so1_cf nta
Source | SS df MS Number of obs =
1680
-------------+------------------------------ F( 4, 1675) =
112.65
Model | 2747.75362 4 686.938406 Prob > F =
0.0000
Residual | 10213.7269 1675 6.0977474 R-squared =
0.2120
-------------+------------------------------ Adj R-squared =
0.2101
Total | 12961.4805 1679 7.71976207 Root MSE =
2.4694
----------------------------------------------------------------------------
--
invest | Coef. Std. Err. t P>|t| [95% Conf.
Interval]
-------------+--------------------------------------------------------------
--
l_tobinq_hat | -4.209413 .5775308 -7.29
0.000 -5.342171 -3.076655
cash | .2018678 .0128175 15.75 0.000 .1767277
.2270079
so1_cf | .4030912 .0384436 10.49 0.000 .3276886
.4784939
nta | -1.561609 .2029786 -7.69
0.000 -1.959727 -1.163491
_cons | 43.40921 5.591037 7.76 0.000 32.44305
54.37536
----------------------------------------------------------------------------
--
.
. ivreg invest cash so1_cf nta (l_tobinq = csk)
Instrumental variables (2SLS) regression
Source | SS df MS Number of obs =
1680
-------------+------------------------------ F( 4, 1675) =
25.33
Model | -32463.2779 4 -8115.81947 Prob > F =
0.0000
Residual | 45424.7584 1675 27.1192587 R-squared =
.
-------------+------------------------------ Adj R-squared =
.
Total | 12961.4805 1679 7.71976207 Root MSE =
5.2076
----------------------------------------------------------------------------
--
invest | Coef. Std. Err. t P>|t| [95% Conf.
Interval]
-------------+--------------------------------------------------------------
--
l_tobinq | -4.209413 1.21795 -3.46
.001 -6.598277 -1.82055
cash | .2018678 .0270308 7.47 0.000 .1488501
.2548855
so1_cf | .4030913 .0810734 4.97 0.000 .2440753
.5621072
nta | -1.561609 .4280597 -3.65
0.000 -2.401197 -.7220208
_cons | 43.40921 11.79089 3.68 0.000 20.28278
66.53564
----------------------------------------------------------------------------
--
Instrumented: l_tobinq
Instruments: cash so1_cf nta csk
----------------------------------------------------------------------------
--
.
Can you tell me the reason?
thanks
Lee Chuntao
*
* 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/
