Welcome to my website. I am Joshua Chan, Professor of Economics at Purdue University, where I hold the endowed Olson Chair.
I am an elected fellow of the International Association for Applied Econometrics. I currently serve as Associate Editor of the Journal of Business and Economic Statistics, the Journal of Applied Econometrics and Stochastic Models. I previously served as Chair of the Economics, Finance and Business Section of the International Society for Bayesian Analysis.
Latest: Getting Started with the Precision Sampler (how-to guides, October 2026); Which Unobserved Components Model Should I Use for Inflation? (tutorial, October 2026)
My current research focuses on scalable Bayesian time series and state space models for empirical macroeconomics, forecasting, and real-time measurement. The three pages below summarize my recent work and provide suggested reading orders, recommended citations, and links to code and replication materials.
- Large Bayesian VARs: shrinkage priors, order invariance, stochastic volatility specification choice, and time variation.
- High-dimensional state space models: efficient Bayesian estimation with missing/mixed-frequency data and scalable computation.
- Trend inflation models: flexible unobserved components models for trend inflation and related extensions.
Book and code. My book Bayesian Macroeconometrics: Methods and Applications (Chapman & Hall/CRC, forthcoming) comes with MATLAB, R and Python code for every chapter. Code for many of my papers is collected in three MATLAB toolkits on GitHub, bvar-toolkit, statespace-toolkit and trend-cycle-toolkit, with tutorials that answer empirical questions and how-to guides that go from a model's equations to working code. Estimates of US trend inflation and the output gap are updated every quarter.