Fuzzy Regression Discontinuity Estimates of the Effects of Public Preschool Enrollment on Maternal Labor Supply, Married Mothers of Four-year-olds in the 2000 Census, Various Sample Widths
| 1 | 2 | 3 | 4 | |
|---|---|---|---|---|
| With No Younger Children | ||||
| Current employment | 0.092 | 0.108 | 0.108 | 0.069 |
| (0.262) | (0.141) | (0.124) | (0.079) | |
| Employment in prior year | 0.212 | 0.145 | 0.085 | 0.012 |
| (0.191) | (0.108) | (0.101) | (0.068) | |
| Weeks worked in prior year | 11.92 | 5.30 | 4.15 | 0.38 |
| (13.35) | (7.06) | (6.22) | (3.77) | |
| Usual hours per week in prior year | 11.06 | 3.67 | 2.62 | −0.61 |
| (6.27) | (4.29) | (4.07) | (2.77) | |
| Wage and salary income, prior year | 3,212 | −2,346 | 565 | 2,082 |
| (11,118) | (6,535) | (5,835) | (3,852) | |
| Welfare receipt in prior year | −0.103 | −0.049 | −0.042 | 0.005 |
| (0.043) | (0.031) | (0.028) | (0.018) | |
| First stage estimate | 0.101 | 0.100 | 0.088 | 0.100 |
| (0.022) | (0.013) | (0.010) | (0.007) | |
| F-statistic | 20 | 56 | 78 | 226 |
| Number of observations | 9,485 | 26,931 | 44,676 | 87,359 |
| With Younger Children | ||||
| Current employment | −0.230 | −0.133 | −0.202 | −0.024 |
| (0.280) | (0.131) | (0.120) | (0.079) | |
| Employment in prior year | 0.125 | 0.056 | 0.100 | 0.120 |
| (0.269) | (0.153) | (0.133) | (0.092) | |
| Weeks worked in prior year | −6.55 | −4.49 | −2.54 | −0.16 |
| (13.01) | (6.79) | (5.81) | (4.08) | |
| Usual hours per week in prior year | 2.12 | −2.20 | −2.36 | 0.07 |
| (10.25) | (5.80) | (5.00) | (3.53) | |
| Wage and salary income, prior year | 5,311 | −12,659 | −14,862 | −7,927 |
| (15,059) | (8,951) | (7,830) | (5,081) | |
| Welfare receipt in prior year | −0.083 | −0.011 | −0.010 | 0.061 |
| (0.134) | (0.057) | (0.047) | (0.033) | |
| First stage estimate | 0.080 | 0.100 | 0.094 | 0.097 |
| (0.030) | (0.017) | (0.013) | (0.009) | |
| F−statistic | 7 | 36 | 55 | 108 |
| Number of observation | 6,272 | 18,182 | 29,893 | 58,881 |
| Width of sample in days | 10 | 30 | 50 | 100 |
Notes: Based on the author’s calculations using the 2000 Restricted Access Long Form Data. Standard errors are in parentheses. Population weights are used when available. Regressions include state fixed effects and the set of controls described in the text. Numbers in bold are significant at the 5 percent level or lower. F Statistics are of the test of the null in which the eligibility for public kindergarten has no effect on public kindergarten enrollment.