07 Giu This type of robustness monitors are given in the baseline review statement (Leap 1000 Research Party 2016)
C. Mathematical Studies
To look at program consequences toward IPV and you can paths, the research exploited the use of a good cutoff endurance used on an ongoing program eligibility index (PMT rating) to recognize treatment and you will review groups. Thus, email address details are valid toward people in the endurance and do maybe not portray a full delivery regarding socioeconomic standing inside the investigation groups. As the an excellent discontinuity can be used into assignment of the cures, i ensure this new problems that generally speaking need to keep having a consistent regression discontinuity framework method of become legitimate within investigation, together with no manipulation during the endurance or expertise in the newest algorithm because of the potential beneficiaries so you’re able to dictate their qualification standing. This new certified take to out of harmony ranging from testing and you can procedures communities is actually including said to your newest try for the dining tables 2 and you may 3 (col. 10). Throughout the complete centering on exercise held, the newest PMT scores varied from ?3.294 so you can cuatro.601 z-results, throughout review test, the latest PMT scores may include ?0.571 in order to 0.324 z-results, toward program qualifications cutoff on ?0.106 z-results ( basic deviation = 0.thirty two ). 6 Households was in fact methodically tested within cutoff having evaluation aim, and the ensuing properties regarding the therapy try is actually inside 0.46 simple deviations of your own cutoff, and all of investigations domiciles are in this 0.43 practical deviations of cutoff. Considering the short threshold of delivery out of tested home to the fresh new PMT score, an easy Performed was applied BBW dating review to check the brand new affects of your program: seven
Manage variables utilized in the research provided personal- and you may home-level symptoms and you may society-top fixed consequences. 8 On individual top, we managed to possess age (in many years) and you may indications when it comes down to formal knowledge regarding one another lady and you may companion. nine After that, during the analysis of your own full sample, i control to be during the a great polygamous partnership (site class was nonpolygamous otherwise, to possess simple dysfunction, a great monogamous union). Household-peak handle details integrated house proportions as well as the PMT get. ten We report the fresh new a style of all of the region signal details for the descriptive equilibrium and attrition tables; although not, once we are people-height fixed outcomes, such evidence are not utilized in regression investigation (districts: East Mamprusi, Karaga, and you may Yendi throughout the North Region and you may Bongo and you can Garu Tempane throughout the Top Eastern Part). To assess distinctions by the family framework, i work together this new sign having polygamous connection with the therapy indication, go out sign, and you may perception guess (creating a multiple communication label): 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.