Figure 1From: Timing and effect of a safe routes to school program on child pedestrian injury risk during school travel hours: Bayesian changepoint and difference-in-differences analysis Quarterly time series with loess trend line and 95% confidence band, school-aged pedestrian crashes per 10 000 population during school-travel (to and from) hours: Safe Routes to School intervention census tracts (yes) versus nonintervention census tracts (no), New York City, 2001–2010. Back to article page