Biostatistics Seminar Series

"Source-sink Reconstruction Through Regularized Multi-component Regression"

Kun Chen, PhD

Assistant Professor

Department of Statistics

University of Connecticut

09/30/2013 ~3:30pm
Room 245, 121 South Main Street, Providence
Refreshments beginning at 3:15pm

The problem of reconstructing the source-sink dynamics arises in many biological systems. Our research is motivated by marine applications where newborns are passively dispersed by ocean currents from several potential spawning sources to settle in various nursery regions that collectively constitute the sink. The reconstruction of the sparse source-sink linkage pattern, i.e., to identify which sources contribute to which regions in the sink, is a challenging task in marine ecology. We derive a constrained nonlinear multi-component regression model for source-sink reconstruction, which is capable of simultaneously selecting important linkages from the sources to the sink regions and making inference about the unobserved spawning activities at the sources. A sparsity-inducing and nonnegativity-constrained regularization approach is developed for model estimation, and theoretically we show that our estimator enjoys the oracle properties. The empirical performance of the method is investigated via simulation studies mimicking real ecological applications. We examine the transport hypothesis that Atlantic cod larvae were transported by sea currents from the North Sea to a few exposed coastal fjords along the Norwegian Skagerrak. We also apply the proposed approach to study the observed jellyfish habitat expansion in the East Bering.