Table 3 Impact of clean buses on attendance overall and by ridership and model year of the replaced buses

From: Randomized design evidence of the attendance benefits of the EPA School Bus Rebate Program

Model

Parameter estimate

95% CI

Overall impact of replacementa

0.06

−0.01 to 0.13

Impact of replacement by ridership on buses requested for replacementa,b

 Quartile 1: 0.05–3.8%

−0.01

−0.15 to 0.14

 Quartile 2: 3.8–8.1%

0.05

−0.05 to 0.16

 Quartile 3: 8.1–16.2%

0.05

−0.10 to 0.19

 Quartile 4: 16.2–100%

0.14

−0.05 to 0.32

Impact of replacement for different model years of replaced busesa,c

 Pre-1990

0.45

0.26 to 0.65

 1990–1999

0.10

−0.03 to 0.23

 2000 and newer

−0.03

−0.16 to 0.09

  1. aThe dependent variable is the attendance rate in the year after the lottery. The model is adjusted for attendance rate in the year before the lottery, as well as EPA region, lottery year and an indicator for having more than one application in a given lottery year.
  2. bThe P value for the interaction term by quartiles of ridership on requested buses was 0.69.
  3. cThe independent variables of interest are three indicator variables for winners who replaced pre-1990, 1990–1999 or 2000 and newer model year buses.
Back to article page