Logit(𝑌ij) = 𝛽 0 +
𝜃𝑡 + 𝛽1𝐺+ 𝛽2𝑡 +
𝛽3𝐺.𝑡 + γ 1W + γ2W.𝑡 +
γ3𝐺.W + γ4W.𝐺.𝑡 + 𝑈𝑖𝑔𝑡 +
𝜀𝑖𝑔𝑡 ….(2)
As equation (1) above, 𝑌 is the binary outcome indicator for adverse
pregnancy outcome 𝛽0 is the intercept.
𝜃𝑡 captures the period of time-invariant fixed effects.
𝐺 is an area indicator for treatment (𝐺 =1) or comparison (𝐺 = 0)
districts. t is an indicator variable for baseline (=0) or endline (=1),
𝛽s are the regression coefficients to be estimated by maximum
likelihood. W indicates the household wealth index. The parameters
γ1, γ2, and γ3 represent
adjusted effects of wealth in comparison districts at baseline, the
change in the effect of wealth in comparison districts between baseline
and end-line, and the difference in the effect of wealth between
intervention and comparison districts at baseline respectively. Thus,γ4 estimates the effect of GEHIP on health
equity relative to comparison districts, that is the difference in
change in equity between intervention and comparison districts. The
vector Uigt refers to control variables in the model
while 𝜀𝑖𝑔𝑡 is the error term. STATA software
was used in all the analyses.