Yunhan Wu

I am a Postdoctoral Research Associate at Oak Ridge National Laboratory in the Biostatistics and Biomedical Informatics Group, led by Dr. Heidi Hanson. My work involves developing statistical methods to support biomedical research, harnessing the power of high-performance computing to solve real-world problems.

I obtained my PhD in Biostatistics from the University of Washington, advised by Dr. Jon Wakefield. My dissertation was Methods and Software for Small Area Estimation in Low- and Middle-Income Countries. As part of this work, the SAE4Health initiative has been adopted at WHO techinical workshops to support health resource planning in low- and middle-income countries.

Before my PhD, I studied Biostatistics as an undergraduate at UNC-Chapel Hill, advised by Dr. Feng-Chang Lin.

My research interests include small area estimation, environmental health, survival analysis, survey methods, and machine learning.

news

Jun 15, 2025	🏆 Honored to receive the Outstanding PhD Student Award from the School of Public Health at University of Washington!
May 20, 2025	Excited to share that I have joined Oak Ridge National Laboratory as a postdoc!

selected publications

JRSSA
Modelling urban/rural fractions in low- and middle-income countries

Yunhan Wu and Jon Wakefield

Journal of the Royal Statistical Society Series A: Statistics in Society, Jan 2024

Abs DOI Bib

In low- and middle-income countries, household surveys are the most reliable data source to examine health and demographic indicators at the subnational level, an exercise in small area estimation. Model-based unit-level models are favoured for producing the subnational estimates at fine scale, such as the admin-2 level. Typically, the surveys employ stratified 2-stage cluster sampling with strata consisting of an urban/rural designation crossed with administrative regions. To avoid bias and increase predictive precision, the stratification should be acknowledged in the analysis. To move from the cluster to the area requires an aggregation step in which the prevalence surface is averaged with respect to population density. This requires estimating a partition of the study area into its urban and rural components, and to do this we experiment with a variety of classification algorithms, including logistic regression, Bayesian additive regression trees, and gradient boosted trees. Pixel-level covariate surfaces are used to improve prediction. We estimate spatial HIV prevalence in women of age 15–49 in Malawi using the stratification/aggregation method we propose.
@article{urbanruralmodeling, author = {Wu, Yunhan and Wakefield, Jon}, title = {Modelling urban/rural fractions in low- and middle-income countries}, journal = {Journal of the Royal Statistical Society Series A: Statistics in Society}, volume = {187}, number = {3}, pages = {811-830}, year = {2024}, month = jan, issn = {0964-1998}, doi = {10.1093/jrsssa/qnae003}, url = {https://doi.org/10.1093/jrsssa/qnae003}, }

Sci. Total Environ.

Integrating traffic pollution dispersion into spatiotemporal NO2 prediction

Yunhan Wu, Jianzhao Bi, Amanda J Gassett, and 3 more authors

Science of The Total Environment, Jan 2024

DOI Bib

@article{wu2024integrating,
  title = {Integrating traffic pollution dispersion into spatiotemporal NO2 prediction},
  author = {Wu, Yunhan and Bi, Jianzhao and Gassett, Amanda J and Young, Michael T and Szpiro, Adam A and Kaufman, Joel D},
  journal = {Science of The Total Environment},
  year = {2024},
  volume = {925},
  pages = {171652},
  doi = {10.1016/j.scitotenv.2023.171652},
}

Report

Spatial modeling for subnational administrative level 2 small-area estimation

Yunhan Wu, Zehang Richard Li, Ben Mayala, and 9 more authors

DHS Spatial Analysis Reports No. 21, Jan 2021

Bib HTML PDF

@article{wu:etal:21,
  title = {Spatial modeling for subnational administrative level 2 small-area estimation},
  institution = {{ICF} International},
  journal = {DHS Spatial Analysis Reports No.~21},
  author = {Wu, Yunhan and Li, Zehang Richard and Mayala, Ben and Wang, Houjie and Gao, Peter and Paige, Johnny and Fuglstad, Geir-Arne and Moe, Caitlin and Godwin, Jessica and Donohue, Rose and Croft, Trevor and Wakefield, Jon},
  year = {2021},
}