Climate change ecology (spring 2025)

Offered within the MIT-WHOI joint program, this course is a data-analysis-intensive topics course where students will use climate impact models to understand the projected changes to marine ecosystems due to anthropogenic climate change. We will specifically use models developed as part of the Fisheries and Marine Ecosystem Model Intercomparison Project (FishMIP; www.fishmip.org).  

Bayesian Modelling of Dynamic Marine Ecological Systems (fall 2020)
Developed with Paul Mattern as part of the Collaboration on Computational Biogeochemical Modelling of Marine Ecosystems (CBIOMES). The workshop materials apply the MCMC package Stan to a series of case studies. All codes to call Stan are written in Julia, R, and Python, inclusively. Lecture materials include a brief introduction to Bayesian inference and the science behind the case studies. GitHub page is here.  Other materials here and here. 

Bayesian modeling of ecological systems using the 'Stan' software package (fall 2020)
Developed with Paul Mattern as part of the Independent Activities Period at MIT. The course develops a Bayesian analysis of a marine ecosystem model via simulation, model fitting, prior specification, predictive analyses, and uncertainty quantification. The model analysis is done in Python. Fitting the model is done in the Stan programming language. GitHub page is here.

Bayesian environmental statistics (spring 2017)

Developed as a special topics course in the Department of Earth System Science at UCI. The course taught the basics of Bayesian statistics using the Stan programming language. Participants brought their own datasets to analyze in the course and also contributed to a group data analysis project that resulted in a peer reviewed publication. 

Introduction to Spatial-Temporal Statistics (spring 2016)
Developed with Yara Mohajerani as part of the Data Science Initiative at UCI. Topics cover introductory concepts in applied time series and spatial analysis using a few key R packages. The notes also include instructions linking Python to R via the package rPy2, allowing Python users to access the many statistics packages in R. GitHub page is here.