Table 1.
Results from the Bayesian changepoint analysis
| Variable | Posterior mean | 95% CrI |
|---|---|---|
| SRTS Intervention | ||
| Changepoint (δ), number of quarters from January 2001 | 30.5 | (30.02, 30.98) |
| β0 (Pre-changepoint intercept) | 1.25 | (0.90, 1.58) |
| β1 (Pre-changepoint slope) | 0.03 | (0.02, 0.05) |
| β2 (Pre- and post intercept difference) | −1.68 | (−2.59, −0.84) |
| β3 (Pre- and post slope difference) | 0.04 | (−0.1, 0.17) |
| β0 + β2 (Post-changepoint intercept) | −0.43 | (−1.45, 0.52) |
| β1 + β3 (Post-changepoint slope) | 0.07 | (−0.06, 0.21) |
| Non-SRTS Intervention | ||
| Changepoint (δ), number of quarters from January 2001 | 10.49 | (10.02, 10.97) |
| β0 (Pre-changepoint intercept) | 4.79 | (4.74, 4.85) |
| β2 (Pre- and post intercept difference) | −0.29 | (−0.36, −0.27) |
| β0 + β2 (Post-changepoint intercept) | 4.50 | (4.46, 4.53) |
Posterior means and 95% Credible Intervals (CrI) on log scale. Safe Routes to School (SRTS) intervention census tracts and non-SRTS intervention census tracts, New York City, 2001–2010.