Wenna Xi

Background

About Wenna Xi

https://wennaxi.github.io/At Weill Cornell, I am using insurance claims data to study the healthcare utilization patterns among patients with mental health disorders. In addition, I am using latent variable modeling technique to uncover patients' true mental health status as well as social constraints that contribute to the under-diagnosis of major depressive disorders (MDDs) using electronic health records (EHR) data.My doctoral dissertation focuses on analyzing co-location networks to detect ecological communities based on people's routine activity locations. Co-location networks are a special type of two-mode networks, where nodes represent individuals and geographic locations and ties indicate that the individual visits the location. Specifically, I used latent Dirichlet allocation (LDA) and hierarchical Bayesian non-negative matrix factorization (NMF) to detect the communities, and the sparse finite mixture techniques to automatically determine the number of communities in a co-location network. You can find a copy of my dissertation here: http://rave.ohiolink.edu/etdc/view?acc_num=osu1566156023255678.Besides my dissertation's research, I have over 7 years of experience in analyzing health-related data and I am proficient in statistical software R, SAS, Stata, JMP, JAGS, and Minitab.