clear
set seed 123456789
set obs 1000
gen x = 5*invnorm(uniform())
gen u = invnorm(uniform())
gen y = 1 + x + u
gen d=y>x
table d
gen d1=d
gen d2=1-d1
gen x1=d1*x
gen x2=d2*x
reg y x1 x2
随便模拟的数据，程序结果如下
. clear
. set seed 123456789
. set obs 1000
obs was 0, now 1000
. gen x = 5*invnorm(uniform())
. gen u = invnorm(uniform())
. gen y = 1 + x + u
. gen d=y>x
. table d
----------------------
d | Freq.
----------+-----------
0 | 156
1 | 844
----------------------
.
. gen d1=d
. gen d2=1-d1
.
. gen x1=d1*x
. gen x2=d2*x
.
. reg y x1 x2
Source | SS df MS Number of obs = 1000
-------------+------------------------------ F( 2, 997) =12762.53
Model | 25150.5031 2 12575.2516 Prob > F = 0.0000
Residual | 982.369613 997 .98532559 R-squared = 0.9624
-------------+------------------------------ Adj R-squared = 0.9623
Total | 26132.8727 999 26.1590318 Root MSE = .99264
------------------------------------------------------------------------------
y | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
x1 | .9986494 .0069737 143.20 0.000 .9849646 1.012334
x2 | 1.0133 .0143129 70.80 0.000 .9852135 1.041387
_cons | 1.017752 .0314014 32.41 0.000 .9561319 1.079373
------------------------------------------------------------------------------
扫码加好友，拉您进群
全部版块
我的主页
收藏
