Test—Retest Correlations, Cronbach’s Alpha, and Influence of Enumerators by Subgroups
| Test–Retest Correlation | Cronbach’s Alpha | R2 of Enumerator FE | |||||||
|---|---|---|---|---|---|---|---|---|---|
| Enumerator Assigned for Test and Retest | By Cognitive Skill | By Cognitive Skill | By Cognitive Skill | ||||||
| Sample Split: | Same | Different | Below Median | Above Median | Below Median | Above Median | All | Below Median | Above Median |
| Cognitive | 0.91 | 0.82 | 0.67 | 0.68 | 0.54 | 0.48 | 0.04 | 0.05 | 0.08 |
| (0.000) | [0.066] | [0.822] | [0.407] | ||||||
| Noncognitive | 0.60 | 0.54 | 0.50 | 0.46 | 0.63 | 0.67 | 0.09 | 0.16 | 0.11 |
| (0.116) | [0.000] | [0.000] | [0.029] | ||||||
| Technical | 0.45 | 0.38 | 0.25 | 0.44 | 0.46 | 0.55 | 0.07 | 0.15 | 0.12 |
| (0.096) | [0.000] | [0.000] | [0.008] | ||||||
Notes: The p-values between parentheses indicate significance of the difference between same and different enumerator assigned for test and retest. R2 of enumerator fixed effects (FE) is the R2 of a regression of the improved construct on (randomly) assigned enumerator fixed effects. The p-values between brackets provide the significance levels of the R2 values. All p-values were obtained by randomization inference (10,000 repetitions).