Versión de HTML Básico
Assessing the Effect of Conditional Cash Transfers in Children Chronic Stunting: The Human Development Bonus in Ecuador
105
13
Analiti a, Revista de análisis estadístico, Vol. 13 (1), 2017
Table 5:
First stage (parametric)
VARIABLES
(1)
(2)
(3)
Z
0,175* 0,176* 0,189**
(0,0925) (0,0928)
(0,0878)
X
0,0232
0,111
0,278
(0,0268)
(0,501)
(0,475)
X2
-0,00154 -0,00435
(0,00881) (0,00833)
age (months)
7,75e-05**
(3,23E-05)
sex (1: male)
0,0296
(0,0378)
ethnicity (1: indigenous)
0,185***
(0,0536)
mother’s height
0,00211
(0,0035)
mother’s education level
-0,166***
(0,0332)
Constant
-0,235 -1,472
-4,023
(0,796)
(7,117)
(6,772)
Observations
662
662
662
Robust standard errors in parentheses
*** p
<
0,01, ** p
<
0,05, * p
<
0,1
Dep var: BDH treatment (D)
Note:
Coefficients of Z in (1), (2) and (3) are parametric estimates of the effect of the
eligibility status on the actual treatment. They are all significant and, for instance,
the quadratic specification estimate can be interpreted as an increase in 19% percent
in the probability of receiving BDH for households in the vicinity with values for the
RSII index as lower as 28.2.
Given the randomness of the discontinuity sample we could describe the effects of Table
6, as those of the BDH over the stunting. Though, not all eligible households effectively
receive the transfer, and some not eligibly end up receiving it. Therefore, the ITT is an
underestimated effect, reason why we require to compute the ratio of this value to the first
stage, also called compliers proportion. In this case the ITT effect of the BDH over stunting
z-scores ranges from -0,41 to -0,34. Nevertheless, only for specification (3) the estimates are
significant and at a 5% level.
The mentioned ratio is the LATE of the benefit on the HAZ for the bandwidth (25,2;31,2).
23