Skip to main content

Research Roundup

Take a dive into the sea of research projects being conducted by our faculty! This only reflects a subset of the vast and diverse research taking place among our faculty members. Learn more below.

Subhashis Ghoshal

National Science Foundation (DMS-Statistics): Collaborative Research: Novel Modeling and Bayesian Analysis of High-dimensional Time Series. Proposal number DMS 2210280. 09/01/2022 – 08/31/2025. Funding level $180,000. Role: PI.

Emily Griffith

Emily Griffith is an investigator on the NC State segment of the recently-renewed NC TraCS proposal (NIH, — in her role, she will build and staff a group of NC State students in the TraCS Electronic Health Records Data Science Lab. The team, led by Emily Griffith, will work to support the data science needs of clinical researchers engaged in high-impact translational and collaborative work through workshops, online educational modules, and one-on-one consulting.

Emily Hector

Funding: North Carolina State University Office of Global Engagement (2023-2024). Scalable statistical approaches for robust and resilient extreme weather adaptation: a new approach to climate science. Role: PI. Description:  This project proposes to build a collaboration with international stakeholders and experts for the development of statistically and computationally efficient models of extreme weather events. The partner institution in this proposal, the University of Edinburgh (UE) in Scotland, is home to leading experts in spatial modeling of climate.

Jacqueline Hughes-Oliver

Hughes-Oliver, J.M. (PI). EMN-21-F-S-01 Predict Diverse System Solubility. Eastman Chemical. $336,379 funded total. Fully Funded. Supports 2 PhD students, one in Statistics, the other in Engineering. Research team includes faculty from the College of Engineering & the College of Veterinary Medicine. January 2022 – September 2023. This project will leverage existing solid-liquid equilibrium data by aggregating them to create a large diverse Conglomerate Dataset. They will also leverage existing machine learning predictive methods for solubility by analyzing their inter-relationships, identifying target areas for expansion and enhancement, then extending applicability to a broad range of solute-solvent systems. Models will be validated using a number of sources, and the final validated model will be delivered to Eastman. This project will benefit from Eastman collaboration to provide information regarding chemical diversity, additional solubility data, and general technical feedback to be more in line with Eastman’s interest.

Wenbin Lu

NIH/NIA R01 Grant (R01AI170254): Modeling of the Viral Load Trajectories for HIV Cure Research (Role: Co-I; PI: Rui Wang at Harvard Medical School), 09/2022 – 08/2026. The goal of this project is to develop novel inference methods and modeling techniques for characterizing the viral rebound process for HIV cure research.

Justin Post

Justin Post is Co-PI of a recently funded NSF IUSE grant NCSU project. The 3-year, $275,484 project is entitled, “Modules for Statistics Graduate Teaching Assistants Learning to Teach Equitably with Authentic Data.” This project aims to design and assess resources for statistics graduate teaching assistants (GTAs) to teach equitably with authentic data. Guided by a design and development research approach, the project will: (1) design a set of four research-informed modules for statistics GTAs learning to teach equitably with authentic data (LEAD Modules), (2) implement LEAD Modules with two GTA communities teaching introductory statistics courses at North Carolina State University and Michigan State University, and (3) further refine LEAD Modules based on design-based research that examines GTA development and their communities. LEAD Modules focus on: (a) teaching statistical thinking, (b) facilitating the model “launch, explore, and discuss,” (c) enacting teacher discourse moves, and (d) promoting participatory equity. By drawing on the interdisciplinary expertise of the principal investigators, the project infuses knowledge bases and resources from statistics education and teacher education to support statistics GTAs’ learning to teach equitably with authentic data. 

Erin Schliep

Sponsor – Office of Naval Research June 2023 – September 2025 Title – Process based data fusion for Marine mammal science Collaborating university – Duke University

Sponsor – National Oceanic & Atmospheric Administration (NOAA) January 2023 – December 2024 Title – Towards Enhanced Understanding of North Atlantic Right Whale Distribution Across Their Entire Habitat Range. Collaborating university – Duke University

Collectively, these two projects aim to develop statistical methods to leverage multiple disparate datasets that inform on different facets of marine mammal abundance in order to better estimate true abundance and quantify uncertainty in these estimates. These data sources include sightings obtained from aerial and shipping transects and passive acoustic monitors that detect sounds made by the mammals. One particular focal species of interest is the North Atlantic right whale, which is one of the world’s most endangered large whale species. Our initial findings are that through a novel data fusion of multiple data sources, we are able to better estimate the abundance of North Atlantic right whales within Cape Cod Bay, Massachusetts. On-going research aims to identify changes in abundance over time, both across years as well as across seasons within the year.

Srijan Sengupta

Title: Wildfire pollution exposure and human health: Building a novel AI-powered air quality forecasting model for a growing public health issue. Period: 03/22–03/23. Amount: $68,224. Role: PI. Funding agency: NCSU Center for Human Health and the Environment. Brief Description: Wildfires emit large quantities of air pollutants into the atmosphere. As wildfires increase in frequency, intensity, duration, and coverage area, such emissions have become a significant health hazard for residential populations, particularly vulnerable groups. This health hazard is exacerbated by two factors: first, wildfires are expected to increase in frequency due to climate change; and second, fine particulate matter, PM2.5, in wildfire smoke adversely impacts human health. Recent toxicological studies suggest that wildfire particulate matter may be more toxic than equal doses of ambient PM2.5. The human health and environmental impact of wildfire are a priority research area for many US federal agencies e.g., NIEHS, US EPA, and NOAA. Our goal is to forecast the human health burden of wildfire emissions via deep learning models. We will develop a novel statistical framework for forecasting future emissions from active wildfires by integrating physicochemical models of emissions and satellite observations with statistical forecasting models. Next, we will model the human health impacts of poor air quality and use this to forecast the burden of diseases associated with exposures to wildfire events, both short- and long-term, and help develop mitigation strategies.

Charles Smith

Charles Smith was recently awarded with a Fulbright Scholar Award. He is using the award to conduct research on statistical and stochastic modeling of postural sway during quiet standing in health and disease at Osaka University’s School of Engineering Sciences in Toyonaka, Japan. His areas of expertise include neurobiology, stochastic processes and physiological models. 

Ana-Maria Staicu

NCSU Seed Grant: Modeling Social Media Information Pathways and Mitigating the Effect of Disinformation (2023-2024). Role co-PI. This project is centered on studying trends related to self-harm, harm towards others, and mental health issues as they are manifested on social media, and it also explores how COVID-19 has influenced these trends.

Len Stefanski

Fractional Ridge Regression. Funding agency: National Science Foundation. $320,000; September 2023 — August 2026. Role: PI. Description: Ridge regression was introduced by Hoerl and Kennard (1970a,b) and twenty-six years later was followed by the introduction of the lasso Tibshirani (1996). The body of research ensuing from these seminal papers is staggering, and has contributed immensely to our understanding of shrinkage and selection methodology and to the practice of regression modeling in many areas of science. In some applications of regression modeling the goal is simply to achieve the best possible predictions of future response values. In other applications, interpretation is important as a way to guide understanding of the process under investigation. Ridge regression is very good at prediction, although is often eclipsed by the lasso in terms of both prediction and interpretation because the lasso also allows for selection. The method to be studied with this grant, fractional ridge regression, has the potential to improve both prediction (as measured by mean square error) and interpretability (as measured by the specificity of variable selection) relative to the lasso.

Shu Yang

Source: NCSU Research and Innovation Seed Funding Climate Change Award, 2023–2024. Title: Harnessing Data Science to Drive Precision Policy for Marine Protected Areas. Role: PI. Description: Preserving marine biological diversity and resilient marine ecosystems have been crucial objectives of governments, conservationists, and ocean scientists. With marine protected areas (MPAs) increasingly used as a climate resilience and development strategy, MPA expansion has been set as an important target for multiple global agreements. The main goal of this proposed work is to draw knowledge from marine conservation and statistical sciences to address these challenges and identify important determinants of MPA effects, toward a powerful paradigm of the precision policy of MPAs.