香蕉视频

Title:听How close and how much? Linking health outcomes to spatial distributions of built environment features.

础产蝉迟谤补肠迟:听Veronica Berrocal is an Associate Professor in the Department of Statistics at UC Irvine (UCI). She joined UCI in Fall 2019, after having spent 9 years as faculty in the Department of Biostatistics at University of Michigan. Veronica earned her Ph.D. in Statistics at University of Washington in 2007, and was a postdoctoral fellow in the Research Triangle Park area for 3 years, performing research first for a year at the US EPA as a National Research Council postdoctoral associate, and then for two years at Duke University/SAMSI. Veronica's research interests are in spatial/spatio-temporal statistics, statistical methods for environmental epidemiology and environmental exposure assessment, with a particular focus on air pollution, climate, weather, and more recently the built environment, in particular as they relate to human health.

Built environment features (BEFs) refer to aspects of the human constructed environment, which may in turn support or restrict health related behaviors and thus impact health. In this talk we will present two approaches to understand whether the spatial distribution and quantity of fast food restaurants (FFRs) influence BMI and the risk of obesity in schoolchildren. The first method is focused on determining the 鈥渞adius of influence鈥� of BEFs on children鈥檚 BMI values and extends the class of Distributed Lag Models to the spatial context. The second method is a two-stage Bayesian hierarchical modeling framework that examines how the spatial pattern and quantity of FFRs affect the risk of obesity. The first stage of the hierarchical model uses the position of FFRs relative to that of some reference locations - in our case, schools - and models them as realizations of 1-dimensional Inhomogenous Poisson processes (IPP). With the goal of identifying representative spatial patterns of exposure to FFRs, we adopt a Bayesian non-parametric viewpoint and provide the intensity functions of the IPPs with a Nested Dirichlet Process prior. The second stage model relates exposure patterns to obesity, offering two different approaches to accommodate uncertainty in the exposure patterns estimated in the first stage.

Our analysis on the influence of patterns of FFR occurrence on obesity among Californian schoolchildren has indicated that, in 2010, among schools that are consistently assigned to a cluster, the odds of obesity amongst 9th graders who attend schools with most distant FFR occurrences in a 1-mile radius are lower than for other schoolchildren.

For Zoom meeting :听Please contact: admincoord.eboh [at] mcgill.ca

听