Component-wise gradient boosting and false discovery control in survival analysis with high-dimensional covariates.

MOTIVATION: Technological advances that allow routine identification of high-dimensional risk factors have led to high demand for statistical techniques that enable full utilization of these rich sources of information for genetics studies. Variable selection for censored outcome data as well as control of false discoveries (i.e. inclusion of irrelevant variables) in the presence of high-dimensional predictors present serious challenges. This article develops a computationally feasible method based on boosting and stability selection. Specifically, we modified the component-wise gradient boosting to improve the computational feasibility and introduced random permutation in stability selection for controlling false discoveries. RESULTS: We have proposed a high-dimensional variable selection method by incorporating stability selection to control false discovery. Comparisons between the proposed method and the commonly used univariate and Lasso approaches for variable selection reveal that the proposed method yields fewer false discoveries. The proposed method is applied to study the associations of 2339 common single-nucleotide polymorphisms (SNPs) with overall survival among cutaneous melanoma (CM) patients. The results have confirmed that BRCA2 pathway SNPs are likely to be associated with overall survival, as reported by previous literature. Moreover, we have identified several new Fanconi anemia (FA) pathway SNPs that are likely to modulate survival of CM patients. AVAILABILITY AND IMPLEMENTATION: The related source code and documents are freely available at https://sites.google.com/site/bestumich/issues. CONTACT: yili@umich.edu.

Physical activity-related and weather-related practices of child care centers from 2 states

© 2015 Human Kinetics, Inc.Background: Young children's physical activity (PA) is influenced by their child care environment. This study assessed PA practices in centers from Massachusetts (MA) and Rhode Island (RI), compared them to best practice recommendations, and assessed differences between states and center profit status. We also assessed weather-related practices. Methods: Sixty percent of MA and 54% of RI directors returned a survey, for a total of 254. Recommendations were 1) daily outdoor play, 2) providing outdoor play area, 3) limiting fixed play structures, 4) variety of portable play equipment, and 5) providing indoor play area. We fit multivariable linear regression models to examine adjusted associations between state, profit status, PA, and weather-related practices. Results: MA did not differ from RI in meeting PA recommendations (β = 0.03; 0.15, 0.21; P = .72), but MA centers scored higher on weather-related practices (β = 0.47; 0.16, 0.79; P = .004). For-profit centers had lower PA scores compared with nonprofits (β = -0.20; 95% CI: -0.38, -0.02; P = .03), but they did not differ for weather (β = 0.12; -0.19, 0.44; P = .44). Conclusions: More MA centers allowed children outside in light rain or snow. For-profit centers had more equipment-both fixed and portable. Results from this study may help inform interventions to increase PA in children.