Skip to main content
. Author manuscript; available in PMC: 2017 Mar 1.
Published in final edited form as: J Health Econ. 2016 Jan 29;46:70–89. doi: 10.1016/j.jhealeco.2016.01.005

Table A5.

Difference-in-difference estimates of the policy’s impact on budget shares (Panel sample)

Pre Post Time difference
A. Budget share spent on alcohol (%)
 CCT 0.073 0.133 0.060
(0.021) (0.133) (0.060)
 Control 0.328 0.204 −0.125
(0.067) (0.038) (0.071)

 Group difference −0.255 −0.071
(0.070) (0.053)

 Difference-in-difference 0.184**
(0.081)
B. Budget share spent on tobacco (%)
 CCT 0.044 0.064 0.020
(0.013) (0.019) (0.016)
 Control 0.146 0.129 −0.017
(0.023) (0.025) (0.031)

 Group difference −0.102 −0.065
(0.026) (0.031)

 Difference-in-difference 0.037
(0.035)
C. Budget share spent on sweets (%)
 CCT 1.051 1.348 0.298
(0.060) (0.074) (0.084)
 Control 1.062 1.062 0.001
(0.105) (0.089) (0.124)

 Group difference −0.011 0.286
(0.121) (0.116)

 Difference-in-difference 0.397**
(0.150)
D. Budget share spent on soft drinks (%)
 CCT 1.110 1.188 0.078
(0.080) (0.071) (0.097)
 Control 1.452 1.627 0.175
(0.092) (0.136) (0.148)

 Group difference −0.341 −0.438
(0.122) (0.153)

 Difference-in-difference −0.097
(0.176)

Note: Robust standard errors, clustered by district, are in parentheses.

Significance:

***

p < 0.01

**

p < 0.05

*

p < 0.10.