IMPACT ON COMMERCIALIZATION 39
matched with the entire sample of comparisons. However, each comparison observation enters the estimate with a weight inversely proportional to its distance to the treatment one, based on the propensity score distribution. In the second method, each treatment observation is matched with the average value of its five nearest comparison neighbors, again based on the propensity score distribution. To ensure maximum comparability of the treatment and comparison groups, the sample is restricted to the common support region, defined as the interval of propensity score values where both treatment and comparison observations can be found.
A straightforward way to test the validity of the matching procedure is to compare an average household’s characteristics in the treatment sample to the corresponding characteristics of the comparison group generated. Accord- ingly, the absence of significant differences between the treatment and com- parison groups is indicative of a valid matching. We thus undertake a series of statistical tests for differences in household characteristics on three differ- ent samples: (1) cooperative members in treatment kebeles compared to all households in the comparison kebeles (an unmatched sample); (2) cooperative members in treatment kebeles compared to the subset of households satisfying the common support restriction in the comparison kebeles, with kernel-based matching; and (3) cooperative members in treatment kebeles compared to the subset of households satisfying the common support restriction in the compari- son kebeles, selected through the five-nearest-neighbors matching method. As shown in Table 3.6, the unmatched sample fails to satisfy the balanc- ing properties: households in treatment kebeles are on average significantly different from the households in the comparison kebeles in all but one of the aspects considered. By comparison, only one such significant difference is observed in the matched samples, that is, the number of ruminants owned by the household. Overall, these results suggest that the two matched sam- ples suit our comparability requirements, whereas the nonmatched sample does not.
Average Impact Indicators of Impact
We assess the impact of cooperatives on smallholders’ commercialization using two related indicators. The first one captures the extent to which cooperatives provide smallholders with better market conditions in the form of higher output prices. The second one measures smallholders’ actual mar- keting response to cooperative membership, as reflected in the percentage of output being commercialized.
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84 |
Page 85 |
Page 86 |
Page 87 |
Page 88 |
Page 89 |
Page 90 |
Page 91 |
Page 92 |
Page 93 |
Page 94 |
Page 95 |
Page 96 |
Page 97 |
Page 98 |
Page 99 |
Page 100 |
Page 101 |
Page 102 |
Page 103