NOTE: N = 2,784 students clustered in 18 intervention schools and 3,070 students clustered in 18 control schools. Generalized linear mixed models (SAS PROC GLIMMIX, Poisson distribution with log link function) were used to evaluate the program impact while accounting for the clustering of students within schools. Covariates in the model included the baseline school mean of the response variable, treatment condition (intervention vs. control), race/ethnicity, sex, number of parents in household, and school size. Program impacts were estimated as a model-adjusted event rate ratio (ERR) for intervention versus controls at follow-up, with 95 percent confidence limits. There are no statistically significant program impacts.
SOURCE: Student survey, fall 2006 (baseline) and spring 2009 (third follow-up).
|