C. Statistical Research
To examine program effects towards the IPV and you may routes, the research cheated the aid of a cutoff tolerance placed on a continuous program qualification list (PMT get) to spot procedures and you will analysis groups. Therefore, email address details are good towards the people within the endurance and you can create maybe not show an entire shipments off socioeconomic status from inside the investigation teams. Since the a great discontinuity is employed into task of the cures, i make sure the brand new problems that usually need to hold to have a regular regression discontinuity construction way of be appropriate within our investigation, as well as zero control in the threshold otherwise experience in new algorithm of the potential beneficiaries so you can dictate the eligibility reputation. The brand new authoritative take to out-of harmony anywhere between investigations and you can medication groups was and additionally said towards newest shot inside tables dos and you can 3 (col. 10). Regarding the full targeting get it done held, the PMT ratings ranged from ?step three.294 so you can 4.601 z-results, while in the comparison decide to try, the fresh new PMT score start from ?0.571 so you can 0.324 z-results, with the program qualifications cutoff in the ?0.106 z-score ( important departure = 0.thirty-two ). six Homes was basically systematically tested around the cutoff having investigations motives, additionally the resulting homes in the therapy shot are contained in this 0.46 standard deviations of cutoff, as well as comparison home are within 0.43 basic deviations of cutoff. Considering the short endurance of your shipment out of sampled properties around this new PMT rating, a straightforward Performed was applied to check the new influences of the program: seven
Handle details utilized in the study included personal- and domestic-height evidence and people-height repaired consequences. 8 At the individual height, i managed to possess ages (in many years) and evidence for your official degree from both girl and partner. 9 Next, within the study of complete decide to try, we manage for being during the good polygamous connection (site classification was nonpolygamous otherwise, to possess easier malfunction, a free Biracial singles dating site monogamous commitment). Household-peak handle variables included domestic size as well as the PMT get. ten We report the brand new means of all the section sign variables in detailed harmony and you will attrition dining tables; although not, as we is area-top fixed effects, these evidence aren’t found in regression study (districts: Eastern Mamprusi, Karaga, and you will Yendi throughout the North Part and you may Bongo and you may Garu Tempane regarding the Higher East Area). To assess distinctions from the family members structure, we work together the signal to own polygamous union towards medication signal, day sign, and you will feeling imagine (doing a triple interaction term): eleven
D. Attrition
Attrition over the panel period has potential to threaten the internal validity and generalizability of the findings. Overall attrition in our analytic sample is approximately 10%, slightly higher than the overall household sample rate of 6.6%, and does not vary significantly between treatment and comparison samples ( p -value = .35 using a simple t-test; Table 1). Further, we investigate whether the sample lost to follow-up differs significantly from our panel sample in terms of IPV outcomes, control variables, or pathway indicators (tables 2, 3). Column 7 shows the mean difference between the sample lost to follow-up in the treatment group, as compared with the same in the comparison group. Column 8 shows the p-value of this difference derived from a regression using treatment to predict the specific indicator, controlling for the PMT score and restricting to attritors. Table 2 shows that across 12 background characteristics and 14 pathway variables, only one is significant at the p < .05 level (there is a statistically significantly higher proportion of the treatment group lost to follow-up as compared with the comparison group in Bongo district). Table 3 shows that across 15 outcome indicators, the only ones to show evidence of differential attrition at p < .05 or lower are those measuring the frequency of sexual IPV (means of those lost to follow-up in the comparison group are slightly higher at .28 vs. the treatment group at .26). These results indicate that the potential for bias in overall findings due to attrition is low. Despite these promising results, we do find that women leaving our sample across both treatment arms differ in terms of background characteristics from those who remain in our sample (p-values shown in cols. 3 and 6). For example, women who leave the sample are generally younger, better educated, in monogamous partnerships (vs. polygamous), and live in smaller households. This may be reflective of rural-to-urban migration or other mobility patterns, although these differences are not generally observed for pathway variables, including indicators of economic standing.
