Paul A. Parker

Paul A. Parker

Assistant Professor

Department of Statistics

University of California, Santa Cruz

Biography

I am currently an assistant professor in the Department of Statistics at the University of California, Santa Cruz. Before this role, I obtained my Ph.D. in Statistics at the University of Missouri, where I was a recipient of the U.S. Census Bureau Dissertation Fellowship, and a recipient of the University of Missouri Population, Education and Health Center Interdisciplinary Doctoral Fellowship. My dissertation work was focused on Bayesian methods for modeling non-Gaussian unit-level survey data under informative sampling, with an emphasis on application to small area estimation. I am broadly interested in modeling dependent data (spatial, temporal, functional, etc.) for a variety of applications including official statistics, social sciences, and environmental sciences. I am also interested in integration of modern machine learning and data science techniques to help improve statistical models.

Interests

  • Bayesian Methods
  • Official Statistics and Survey Methods
  • Dependent Data (Spatial, Time Series, Functional Data, etc.)
  • Business and Government Applications
  • Deep Learning
  • Data Science

Education

  • Ph.D. in Statistics, 2021

    University of Missouri

  • M.A. in Statistics, 2018

    University of Missouri

  • B.S. in Applied Mathematics, 2014

    University of Idaho

Experience

 
 
 
 
 

Research Mathematical Statistician

U.S. Census Bureau

Mar 2022 – Mar 2025 Center for Statistical Research and Methodology
 
 
 
 
 

Assistant Professor

Department of Statistics

Jul 2021 – Present University of California, Santa Cruz
 
 
 
 
 

Graduate Research Fellow

Census Bureau Dissertation Fellowship

Aug 2019 – Jul 2021 University of Missouri
 
 
 
 
 

Graduate Research Fellow

Population, Education and Health Center Fellowship

Aug 2018 – May 2019 University of Missouri

Projects

Machine Learning for Complex Scientific and Social Data

Developing AI methods for spatial, temporal, and structured datasets.

Mapping Community Level Outcomes

Estimating local population quantities when data are scarce.

Measuring Social and Economic Change

Using data from national surveys to understand migration, inequality, and demographic change.

Statistical Methods for Complex and Dependent Data

Building statistical tools for spatial, temporal, and functional datasets.

Understanding Environmental Processes

Using statistical models to study soil health, the ocean, climate, and other environmental systems.

Software

nlfh

nlfh is an R package that fits nonlinear Bayesian extensions of the Fay–Herriot model for small area estimation. It provides tools for model fitting, prediction, uncertainty summaries, and diagnostics using area-level direct estimates and their sampling variances.

install.packages("nlfh")

CRAN documentation · Source code

vmsae

vmsae is an R package that implements variational multivariate spatial small area estimation models. It provides efficient variational autoencoder-based methods, with NumPyro and PyTorch backends, for estimating population quantities across multiple outcomes and areas.

install.packages("vmsae")

CRAN documentation · Source code

Research Group

I have advised a number of graduate students and postdocs, who have won numerous awards for their research. Those who have graduated have successfully obtained positions in both industry and academia.

If you are interested in working with me, please send me an email describing your background and research interests.

Postdocs

Avatar

Namitha V. Pais

Former Postdoc

Avatar

Parul V. Patil

Current Postdoc

PhD Students

Avatar

Aubree Krager

Current Student

Avatar

Ethan Pawl

Current Student

Avatar

Lyndsey Umsted

Current Student

Avatar

Qi Wang

Former Student

Avatar

Sho Kawano

Current Student

MS Students

Avatar

Adam Slivinsky

Former Student

CV

Find a PDF of my CV here.

Recent Posts

Nonlinear Small Area Estimation in R with nlfh

A practical introduction to nonlinear Fay-Herriot models using the nlfh R package, with an application to median income across Missouri census tracts.

Making a Difference with Data: The Essential Role of Official Statistics

In a world driven by data, few fields are as impactful and essential as official statistics. Whether it’s tracking poverty rates, monitoring public health trends, or guiding economic policies, the field of official statistics serves as the backbone of informed decision-making in society.

Conditional Probability Density Functions

[Note: This post was created as part of a lecture for STAT 131 at UCSC.] Recall that for two continuous random variables \(X\) and \(Y\), we work with the joint probability density function \(f(x,y)\).

Contact

  • Department of Statistics, University of California Santa Cruz, Santa Cruz, CA 95064