My research interests span the topics of statistical modeling and analysis for geographically referenced data, Bayesian statistics (theory and methods), statistical computing and related software development.
Publications
Zhang, L.*, Tang, W.* & Banerjee, S. (2023+) Fixed-Domain Asymptotics Under Vecchia’s Approximation of Spatial Process Likelihoods. Statistica Sinica (accepted) arXiv preprint
Zhang, L., Carpenter, B., Gelman, A. & Vehtari, A. (2022) Pathfinder: Parallel quasi-Newton variational inference Journal of Machine Learning Research link
Zhang, L. (2022) Applications of Conjugate Gradient in Bayesian computation. Wiley StatsRef-Statistics Reference Online link
Tang, W.*, Zhang, L.*, & Banerjee, S. (2021) On identifiability and consistency of the nugget in Gaussian spatial process models. Journal of the Royal Statistical Society Series B link
Zhang, L. & Banerjee, S. (2021). Spatial factor modeling: A Bayesian matrix‐normal approach for misaligned data. Biometrics. link
Zhang, L., Banerjee, S. & Finley, A. O. (2021). High‐dimensional multivariate geostatistics: A Bayesian matrix‐normal approach. Environmetrics. link
Watson, G.L., Xiong, D., Zhang, L., Zoller, J.A., Shamshoian, J., Sundin, P., Bufford, T., Rimoin, A.W., Suchard, M.A. and Ramirez, C.M., (2021). Pandemic velocity: forecasting COVID-19 in the US with a machine learning & Bayesian time series compartmental model. PLOS Computational Biology. prepint
Xiong, D.*, Zhang, L.*, Watson, G.L., Sundin, P., Bufford, T., Zoller, J.A., Shamshoian, J., Suchard, M.A. and Ramirez, C.M., (2020). Pseudo-likelihood based logistic regression for estimating COVID-19 infection and case fatality rates by gender, race, and age in California. Epidemics link
Zhang, L., Datta, A. & Banerjee, S. (2019). Practical Bayesian modeling and inference for massive spatial data sets on modest computing environments. Statistical Analysis and Data Mining: The ASA Data Science Journal link
Preprints
Zhang, L., Tang, W. & Banerjee, S. Exact Bayesian Geostatistics Using Predictive Stacking. arXiv preprint
Sparkes, S.† & Zhang, L.. Properties and Deviations of Random Sums of Densely Dependent Random Variables, arXiv preprint
Liu, S.† & Zhang, L.. Deep Feature Gaussian Processes for Single-Scene Aerosol Optical Depth Reconstruction.
Zhang, L., Finley, A., Nothdurft, A. & Banerjee, S. Bayesian Modeling of Incompatible Spatial Data: A Case Study Involving Post-Adrian Storm Forest Damage Assessment, arXiv preprint
Sparkes, S.†, Garcia, E. & Zhang, L.. The functional average treatment effect, arXiv preprint
(* co-first author, † students mentored by me)
Notes
Stan case study of Nearest neighbor Gaussian process (NNGP) based models link
A Note on using Kullback-Leibler Divergence to compare the performance of some Nearest Neighbor Gaussian Process (NNGP) based models link (HTML)
Packages
JALAJni JaLAJni is a JAVA package providing a java interface for lapack and blas library
JAMAJniLite JAMAJniLite is a JAVA package providing a java interface for lapack and blas libraries and using the classes defined by JAMA Package.
phase1PRMD Implements Bayesian phase I repeated measurement design that accounts for multidimensional toxicity endpoints and longitudinal efficacy measure from multiple treatment cycles and allows individualized dose modification.