10
mhbounds
|
d |
Coef. |
Std. Err. |
z |
P>|z| |
[95% Conf. |
Interval] |
|
age |
.3316904 |
.1203295 |
2.76 |
0.006 |
.0958489 |
.5675318 |
|
age2 |
-.0063668 |
.0018554 |
-3.43 |
0.001 |
-.0100033 |
-.0027303 |
|
education |
.8492683 |
.3477041 |
2.44 |
0.015 |
.1677807 |
1.530756 |
|
educ2 |
-.0506202 |
.0172492 |
-2.93 |
0.003 |
-.084428 |
-.0168124 |
|
married |
-1.885542 |
.2993282 |
-6.30 |
0.000 |
-2.472214 |
-1.298869 |
|
black |
1.135973 |
.3517793 |
3.23 |
0.001 |
.446498 |
1.825447 |
|
hispanic |
1.96902 |
.5668567 |
3.47 |
0.001 |
.8580017 |
3.080039 |
|
re74 |
-.0001059 |
.0000353 |
-3.00 |
0.003 |
-.000175 |
-.0000368 |
|
re75 |
-.0002169 |
.0000414 |
-5.24 |
0.000 |
-.000298 |
-.0001357 |
|
re742 |
2.39e-09 |
6.43e-10 |
3.72 |
0.000 |
1.13e-09 |
3.65e-09 |
|
re752 |
1.36e-10 |
6.55e-10 |
0.21 |
0.836 |
-1.15e-09 |
1.42e-09 |
|
blacku74 |
2.144129 |
.4268089 |
5.02 |
0.000 |
1.307599 |
2.980659 |
|
_cons |
-7.474742 |
2.443502 |
-3.06 |
0.002 |
-12.26392 |
-2.685566 |
Note: 22 failures and 0 successes completely determined.
There are observations with identical propensity score values.
The sort order of the data could affect your results.
Make sure that the sort order is random before calling psmatch2.
|
Γ Sample ∣ |
Treated |
Controls |
Difference |
S.E. | ||
|
Variable | ||||||
|
> |
T-stat |
__________________L | ||||
|
employment |
Γ Unmatched ∣ |
.756756757 |
.885140562 |
-.128383805 |
.024978843 | |
|
> |
-5.14 | |||||
|
ATT I |
.756756757 |
.664864865 |
.091891892 |
.047025406 | ||
|
> |
1.95 | |||||
|
I | ||||||
Note: S.E. for ATT does not take into account that the propensity score is esti
> mated.
|
psmatch2: Treatment |
psmatch2: | |
|
support |
Total | |
|
Untreated |
2,490 |
2,490 |
|
Treated |
185 |
185 |
|
Total |
2,675 |
2,675 |
What can be seen from the output is that we get a significant positive treatment
effect on the treated of 0.0919. That is the employment rate of participants is 9.2%-
points higher when compared to matched control group members. Since psmatch2
automatically produces the variables .treated, .weight, and .support we do not have
to specify those when using mhbounds.
. mhbounds employment, gamma(1 (0.05) 1.5)
Mantel-Haenszel (1959) bounds for variable employment
Gamma Q_mh+ Q_mh- p_mh+ p_mh-
-------------------------------------------------
1 1.83216 1.83216 .033464 .033464
1.05 1.62209 2.04761 .052392 .020299
More intriguing information
1. Whatever happened to competition in space agency procurement? The case of NASA2. Investment in Next Generation Networks and the Role of Regulation: A Real Option Approach
3. The Effects of Reforming the Chinese Dual-Track Price System
4. Chebyshev polynomial approximation to approximate partial differential equations
5. The name is absent
6. Kharaj and land proprietary right in the sixteenth century: An example of law and economics
7. The name is absent
8. The name is absent
9. Multimedia as a Cognitive Tool
10. Staying on the Dole