Rural cooperative warehouse-receipt collateral rules and smallholder cotton-selling timing in Burkina Faso: a regression-discontinuity analysis of receipt-eligibility thresholds

Regression-discontinuity designs are increasingly proposed for evaluating the effects of cooperative warehouse-receipt collateral rules on smallholder selling behaviour, yet the credibility of such evaluations depends on design features that are rarely examined before fieldwork begins. the present analysis characterises the operating characteristics of a regression-discontinuity design applied to receipt-eligibility thresholds in Burkinabè cotton cooperatives, using a design-based power analysis rather than observational data. The analysis specifies a before-after-control-impact variance structure with a between-cluster standard deviation of 6.0, a residual standard deviation of 4.5 and an intraclass correlation of 0.64, and evaluates power across 2000 replications per design cell for cluster counts of 8, 16, 24 and 32 and effect sizes of 3, 5 and 8 percentage points. Power curves, minimum detectable effect curves, coefficient plots, residual diagnostics and receiver operating characteristic curves are reported. The design attains 80 per cent power at a 5 percentage-point effect with 54 clusters, and the minimum detectable effect declines steeply as cluster count rises from 8 to 32. Threshold-based evaluations of cooperative collateral rules are feasible only when the cluster budget is matched to the smallest policy-relevant effect, and it specifies the conditions under which regression-discontinuity estimates of selling-timing effects can be interpreted causally.