Table 5.
Panel A: Horizontal equity analysis: Household level (N = 1603; F < 0.0001) |
Panel B: Vertical equity analysis: Individual level (N = 8663; F < 0.0001) |
|||||||
Level of Analysis | All Nets | Treated nets | All Nets | Treated nets | ||||
Marginal/Average effects† | Marginal/Average effects | Marginal/Average effects | Marginal/Average effects | |||||
Explanatory variable | dF/dx | p-value | dF/dx | p-value | dF/dx | p-value | dF/dx | p-value |
Family size | 0.001 | 0.973 | -0.002 | 0.656 | -0.274 | <0.001* | -0.008 | <0.001* |
Male | -0.032 | 0.555 | -0.01 | 0.859 | -0.056 | <0.001* | -0.02 | 0.023* |
Urban | 0.228 | <0.001* | 0.205 | <0.001* | 0.315 | <0.001* | 0.192 | <0.001* |
Married | 0.007 | 0.887 | 0.043 | 0.408 | 0.031 | 0.051* | 0.04 | <0.001* |
Sambaa | 0.072 | 0.214 | 0.031 | 0.496 | -0.087 | 0.003* | 0.011 | 0.546 |
Digo | -0.085 | 0.108 | -0.102 | 0.012* | -0.176 | 0.001* | -0.086 | 0.001* |
Bondei | 0.079 | 0.248 | -0.051 | 0.314 | -0.05 | 0.15 | -0.056 | 0.005* |
Other ethnic group | 0.006 | 0.908 | -0.078 | 0.048* | -0.09 | 0.001* | -0.056 | <0.001* |
Age of household head | -0.002 | 0.097 | -0.001 | 0.133 | n/a | n/a | n/a | n/a |
Under-five | n/a | n/a | n/a | n/a | 0.157 | <0.001* | 0.06 | <0.001* |
Using other prevention measures | -0.232 | <0.001* | -0.006 | 0.81 | -0.182 | <0.001* | -0.004 | 0.684 |
Education | 0.013 | 0.008* | 0.02 | <0.001* | 0.018 | <0.001* | 0.02 | <0.001* |
Wealth | 0.11 | <0.001* | 0.053 | <0.001* | 0.091 | 0.001* | 0.043 | <0.001* |
Education-squared | -0.002 | 0.028* | -0.001 | 0.073 | n/a | n/a | n/a | n/a |
Wealth-squared | -0.008 | <0.001* | -0.004 | <0.001* | -0.007 | 0.001* | -0.004 | <0.001* |
Poor Road | 0.012 | 0.698 | -0.07 | 0.085 | n/a | n/a | n/a | n/a |
Market centre | -0.016 | 0.764 | -0.008 | 0.906 | n/a | n/a | n/a | n/a |
Constant | - | - | - | - | - | - | - | - |
* Coefficient significant at 5% level
†marginal (average) effects are computed using the dprobit command and reflect the effect of a unity change in the continuous (dummy) variable on the dependent variable.