C. Analytical Data

To look at program outcomes for the IPV and you will pathways, the analysis cheated employing an effective cutoff tolerance used on an ongoing system qualifications list (PMT rating) to identify medication and you may comparison organizations. Thus, results are appropriate to your inhabitants within tolerance and you may carry out perhaps not represent an entire delivery out-of socioeconomic standing for the study groups. Just like the a good discontinuity is used toward task of one’s procedures, we verify the fresh conditions that usually need keep to have an everyday regression discontinuity structure way of become valid in our data, in addition to no manipulation during the endurance or knowledge of the formula by the possible beneficiaries so you can influence the eligibility standing. This new authoritative sample regarding harmony ranging from comparison and you will cures groups are and additionally advertised on the latest test within the dining tables 2 and 3 (col. 10). On the complete targeting do so held, the latest PMT results varied of ?step 3.294 to 4.601 z-score, during research shot, the newest PMT results are priced between ?0.571 to help you 0.324 z-ratings, into system qualifications cutoff at the ?0.106 z-scores ( standard deviation = 0.thirty two ). 6 Domiciles had been methodically sampled around the cutoff to possess research purposes, together with resulting domiciles on therapy take to is actually contained in this 0.46 simple deviations of one’s cutoff, as well as investigations domiciles was in this 0.43 fundamental deviations of your cutoff. Because of the quick endurance of your own shipments out of tested house around the fresh PMT score, a simple Did was used to test the fresh new affects of program: 7

Control details utilized in the study incorporated personal- and family-height indicators and you can society-level repaired outcomes. 8 From the individual top, i regulated to have years (in years) and indicators for the formal education out-of each other woman and you may partner. nine Further, inside research of the full sample, i handle if you are when you look at the a polygamous partnership (reference Dating over 60 dating app category is actually nonpolygamous or, to have easier breakdown, an effective monogamous connection). Household-peak control variables provided home proportions therefore the PMT rating. 10 I statement brand new manner of the region signal parameters inside detailed balance and you will attrition tables; although not, once we are neighborhood-peak fixed outcomes, such symptoms commonly used in regression study (districts: Eastern Mamprusi, Karaga, and you may Yendi regarding North Area and Bongo and you may Garu Tempane regarding the Higher Eastern Region). To evaluate differences by friends design, we interact the fresh new indication getting polygamous commitment to your treatment sign, time signal, and you may effect imagine (starting a multiple correspondence title): 11

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.