We focus on challenges that arise in modern datasets and multi-view learning. Our methods development is motivated by applications in molecular microbiology, microbiome multi-omics, spatial multi-omics, and loss reserves in non-life insurance. Some areas that we use to develop methods include matrix factorization, mixture models, generative models, approximation theory, nonparametric statistics, computational statistics, spatial statistics, Bayesian modeling, and Bayesian sampling methods.
|Pengfei Cai||Ph.D. student in statistics||Prediction on multiple loss triangles: application to loss reserve in multiple business lines||Co-supervision with Dr. Anas Abdallah, 2021-2024|
|Inwook Black||Ph.D. student in statistics||Replicated (multiple view) spatial point pattern: application to spatial omics||expect to start in Fall 2022|
|Ishanka Fernando||M.Sc. student in statistics||Multiple (structured) count matrices: application to microbiome data||expect to start in Fall 2022|
|Shiheng Huang||Undergraduate thesis student||Replicated (multivariate marked) spatial point pattern: application to the analysis of the brain tumor samples||expect to start in Fall 2022|
|Hainan Xu||Undergraduate research student||Spatial point pattern summaries of multiple views: application to the analysis of the primary visual cortex||James Stewart Student Research Award, May - July 2022|
|Mariana Mariles Torres||Undergraduate Research Assistant||Monte Carlo experiments for generative models with goodness-of-fit measures: application to microbiome data||Fall 2021 - Winter 2022|
|Ka Yat Liu||Undergraduate research student||Prior sensitivity analysis and multiplicative noise effects in Bayesian sampling methods: application to microbiome data, https://github.com/kaidenliu0806/summer_research||James Stewart Student Research Award, May - August 2021|
|Gheeda Mourtada||Undergraduate research student||Spatial point pattern summaries for spatial count matrix: application to spatial proteomics data||NSERC USRA, May - August 2021|
Please look at Join Us for more details.