蓝色 发表于 2010-10-26 07:45
程序是没有问题的。
我用他提供的部分数据都能运行出来的。
.
. by company_id: gen event_window=1 if dif>=-2 & dif F = 0.0000
Residual | 2.35542648 28 .084122374 R-squared = 0.7849
-------------+------------------------------ Adj R-squared = 0.7772
Total | 10.9507674 29 .377612668 Root MSE = .29004
------------------------------------------------------------------------------
ret | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
market_ret~n | .0071517 .0007075 10.11 0.000 .0057025 .008601
_cons | -31.10621 8.189216 -3.80 0.001 -47.88105 -14.33136
------------------------------------------------------------------------------
(option xb assumed; fitted values)
(7981 missing values generated)
(5 real changes made)
+---------------+
| id compan~d |
|---------------|
3378. | 3 Opel |
+---------------+
Source | SS df MS Number of obs = 30
-------------+------------------------------ F( 1, 28) = .
Model | .00298667 1 .00298667 Prob > F = .
Residual | 0 28 0 R-squared = 1.0000
-------------+------------------------------ Adj R-squared = 1.0000
Total | .00298667 29 .000102989 Root MSE = 0
------------------------------------------------------------------------------
ret | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
market_ret~n | -.0000875 . . . . .
_cons | .7557923 . . . . .
------------------------------------------------------------------------------
(option xb assumed; fitted values)
(2850 missing values generated)
(5 real changes made)
版主,能再帮我运行下么,我私下给你我的数据,因为我一直就出不来你这样的
. forvalues i=1(1)`N' {
2.
. list id company_id if id==`i' & dif==0
3.
. reg ret market_return if id==`i' & estimation_window==1
4.
. predict p if id==`i'
5.
. replace predicted_return = p if id==`i' & event_window==1
6.
. drop p
7.
. }
+---------------+
| id compan~d |
|---------------|
528. | 1 GM |
+---------------+
Source | SS df MS Number of obs = 30
-------------+------------------------------ F( 1, 28) = .
Model | .000746667 1 .000746667 Prob > F = .
Residual | 0 28 0 R-squared = 1.0000
-------------+------------------------------ Adj R-squared = 1.0000
Total | .000746667 29 .000025747 Root MSE = 0
------------------------------------------------------------------------------
ret | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
market_ret~n | .0000266 . . . . .
_cons | .4374429 . . . . .
------------------------------------------------------------------------------
(option xb assumed; fitted values)
(9858 missing values generated)
variable predicted_return not found
r(111);