Model detection and estimation for single-index varying coefficient model

Penalized estimation of a class of single-index varying-coefficient models for integrative genomic analysis

Recent technological advances have made it possible to collect high-dimensional genomic data along with clinical data on a large number of subjects. In the studies of chronic diseases such as cancer, it is of great interest to integrate clinical and genomic data to build a comprehensive understanding of the disease mechanisms. Despite extensive studies on integrative analysis, it remains an ongoing challenge to model the interaction effects between clinical and genomic variables, due to high dimensionality of the data and heterogeneity across data types. In this paper, we propose an integrative approach that models interaction effects using a single-index varying-coefficient model, where the effects of genomic features can be modified by clinical variables. We propose a penalized approach for separate selection of main and interaction effects. Notably, the proposed methods can be applied to right-censored survival outcomes based on a Cox proportional hazards model. We demonstrate the advantages of the proposed methods through extensive simulation studies and provide applications to a motivating cancer genomic study.

Semiparametric model selection for identification of environmental covariates related to adult groundfish catches and weights

Ecologists and fisheries managers are interested in monitoring economically important marine fish species and using this data to inform management strategies. Determining environmental factors that best predict changes in these populations, particularly under rapid climate change, are a priority. I illustrate the application of the least squares-based spline estimation and group LASSO (LSSGLASSO) procedure for selection of coefficient functions in single index varying coefficient models (SIVCMs) on an ecological data set that includes spatiotemporal environmental covariates suspected to play a role in the catches and weights of six groundfish species. Temporal trends in variable selection were apparent, though the selection of variables was largely unrelated to common North Pacific climate indices. These results indicate that the strength of an environmental variable’s effect on a groundfish population may change over time, and not necessarily in-step with known low-frequency patterns of ocean-climate variability commonly attributable to large-scale regime shifts in the North Pacific. My application of the LSSGLASSO procedure for SIVCMs to deep water species using environmental data from various sources illustrates how variable selection with a flexible model structure can produce informative inference for remote and hard-to-reach animal populations.