Versión de HTML Básico
Assessing the Effect of Conditional Cash Transfers in Children Chronic Stunting: The Human Development Bonus in Ecuador
103
13
Analiti a, Revista de análisis estadístico, Vol. 13 (1), 2017
Figure 5:
Covariate balance tests
Note:
a, b, c and d show local polynomial functions of the forcing variable for the different
covariates in the y-axis. Each point estimate is the mean of the covariate value within the bin in
an equally-spaced partitioning (triangular kernel) of the RSII index. The plots evidence no jumps
at the discontinuity of 28,2 of the estimates of the characteristics of the kids (age and indigenous
ethnicity) nor the mothers (height and education level); which, empirically supports the thesis of
the un-confoundedness of the effect estimate.
Table 4:
BDH compliance
Z
Total
0
1
D
0 3,517 795
4,312
1 680 1,325 2,005
Total
4,197 2,12
6,317
Note:
This cross-tabulation of the actual treatment (D) and the legibility
status (Z) allows as to inspect the proportion of compliers in the total
sample. This is calculated as follows: (D=1/Z=1) - (D=1/Z=0) = 0,63-
0,16=0,46
21