Covariate Balance (Full Sample with Imputed Values)
| Variable | Samplea | Mean Value PSA | Mean Value Non-PSAb | Diff. Mean Value | Raw eQQ Diff.c |
|---|---|---|---|---|---|
| 1992 forest cover (ha) | Unmatched | 86.13 | 38.21 | 47.92 | 20.09 |
| Matched | 86.13 | 68.99 | 17.13 | 4.96 | |
| Farm size (ha) | Unmatched | 165.11 | 71.43 | 93.68 | 40.00 |
| Matched | 165.11 | 108.46 | 56.65 | 17.00 | |
| Participation in past forestry programs | Unmatched | 0.32 | 0.15 | 0.17 | 0.17 |
| Matched | 0.32 | 0.28 | 0.03 | 0.03 | |
| Distance to extension office (km) | Unmatched | 30.10 | 24.60 | 5.50 | 5.00 |
| Matched | 30.10 | 27.78 | 2.33 | 1.00 | |
| % Farm on steep slopes | Unmatched | 38.40 | 25.14 | 13.26 | 10.00 |
| Matched | 38.40 | 38.11 | 0.29 | 0.00 | |
| Forest cover change 1986–1992 | Unmatched | − 11.35 | − 10.83 | − 0.52 | 5.89 |
| Matched | − 11.35 | − 8.33 | − 3.02 | 2.00 |
Note: PSA, Costa Rica’s Programa de Pagos por Servicios Ambientales.
↵a N = 202; 50 PSA farms.
↵b Weighted means for matched controls.
↵c Mean (for categorical covariate) or median (for continuous covariate) difference in the empirical quantile-quantile plot of treatment and control groups on the scale in which the covariate is measured.