Joonha Park's webpage

I am an assistant professor in the Mathematics department at the University of Kansas (from August 2020). Email:

About me

Research interests

My main area of research is computational statistics. I develop Sequential Monte Carlo (SMC) methods and Markov chain Monte Carlo (MCMC) methods. I have interests in spatio-temporal inference, applications to public health/epidemiological data analysis, Bayesian statistics (mainly from the computational perspectives), stability properties of Markov chains, and deep neural networks.


I earned my Ph.D. in Statistics at the University of Michigan in June 2018 under the supervision of Professor Edward Ionides. After that, I worked as a postdoctoral research associate at the Department of Mathematics and Statistics at Boston University, under the supervision of professor Yves Atchade.

My recent work

Inference for spatio-temporal partially observed Markov processes

I have been developing a moderately scalable inference methodology for coupled stochastic dynamic models, such as those arising from spatio-temporal transmission dynamics of infectious diseases. Here is a recently published paper:

  • Park, J. and Ionides, E. L. (2020) Inference on high-dimensional implicit dynamic models using a guided intermediate resampling filter. Statistics and Computing, doi: 10.1007/s11222-020-09957-3. view-only version available at

The implementation of related methods, including the codes and the data, can be found at the Github repository

  • An R package SpatPomp is available (under continual developments) This package enables the users to define their models at an abstract level, and analyze data by using statistical methodologies. The SpatPomp package is an extension of the pomp package, and is developed for coupled, partially observed, Markov process models.

Markov chain Monte Carlo with sequential proposals (sp-MCMC):

A straightforward extension of the Metropolis-Hastings strategy in constructing Markov chains with a target invariant density can be made by allowing sequential proposals. The acceptance/rejection of the sequential proposals are coupled via a shared critical value which is drawn from the uniform(0,1) distribution.

This sequential-proposal framework is flexible, and enables developments of state-of-the-art algorithms. For example, we developed two variants of the NUTS algorithm, and a discrete-time bouncy particle sampler method. For more information, see the following paper.

Other published papers

  • Ionides, E. L., Breto, C., Park, J., Smith, R. A. and King, A. A. (2017) Monte Carlo profile confidence intervals for dynamic systems. Journal of The Royal Society Interface, 14, 20170126.

  • Koopman, J. S., Henry, C. J., Park, J., Eisenberg, M. C., Ionides, E. L. and Eisenberg, J. N. (2017) Dynamics affecting the risk of silent circulation when oral polio vaccination is stopped. Epidemics.

  • Kim, S.-H., Park, J. H., Yoon, W., Ra, W.-S. and Whang, I.-H. (2017) A note on sensor arrangement for long-distance target localization. Signal Processing, 133, 18–31.

ArXiv preprints and manuscripts under preparation:

  • Ionides, E. L., Asfaw, K., Park, J., and King, A. A. (2020+) Bagged filters for partially observed spatiotemporal systems.

  • Asfaw, L., Ionides, E. L., King, A. A., Park, J., and Ho, A. (2020+) Statistical Inference for Spatiotemporal Partially Observed Markov Processes via the R Package spatPomp.

  • Park, J. and Atchadé, Y. (2020+) Hamiltonian Monte Carlo for Bayesian variable selection.