Repairing the Leaky Pipeline: A Motivationally Supportive Intervention to Enhance Persistence in Undergraduate Science Pathways.

The current study reports on the efficacy of a multi-faceted motivationally designed undergraduate enrichment summer program for supporting science, technology, engineering and math (STEM) persistence. Structural equation modeling was used to compare summer program participants ( = 186), who participated in the program between their first and second years in college, to a propensity score matched comparison sample ( = 401). Participation in the summer program positively predicted science motivation (self-efficacy, task value), assessed eight months after the end of the program (second year in college).

Variable selection for binary spatial regression: Penalized quasi-likelihood approach.

We consider the problem of selecting covariates in a spatial regression model when the response is binary. Penalized likelihood-based approach is proved to be effective for both variable selection and estimation simultaneously. In the context of a spatially dependent binary variable, an uniquely interpretable likelihood is not available, rather a quasi-likelihood might be more suitable.