The NYU School of Global Public Health is home to an ecosystem of dynamic centers, labs, and initiatives dedicated to advancing the frontiers of health. Our Biostatistics research groups labs a collaborative environment where students receive expert mentorship and engage in high-impact, action-based learning. Explore our faculty-led labs below to see how we are transforming data into public health solutions.
- Dr. Betensky’s Research Lab
- The Center for Health Data Science (CHDS)
- The Attachment and Health Disparities Research Lab (AHDL)
- The Biostatistical Collaboration and Consultation Core (BC3)
- The Feng Lab
- Dr. Heng’s Research Lab
- Dr. Mei’s Research Lab
- Dr. Shu’s Research Lab
- The Xu Quantitative Lab
- Dr. Zhou’s Research Lab
Dr. Betensky’s Research Lab
Students work in small groups on problems in survival analysis and clinical trial design. They begin by learning the relevant background material and reading the literature. They then consider novel methods, which they study in extensive simulations and in application to data. They meet regularly with Prof. Betensky to discuss their progress and to develop next steps. Current research topics include competing risks with possible early termination of risk, right truncation with censored truncation times and left censored event times, and futility clinical trial designs using the Win Ratio. Current applications are to Alzheimer’s cohort studies and the FDA’s Adverse Event Reporting System (FAERS) database. Projects are supported by an NIH grant for statistical methodology.
The Center for Health Data Science (CHDS)
The Center for Health Data Science (CHDS) led by Dr. Rumi Chunara advances methodological and applied research at the intersection of data science and public health. We develop statistical, computational, and machine learning approaches to address population health challenges, including methods in causal inference, domain adaptation, representation learning, and multimodal modeling. The Center brings together diverse evidence, perspectives, and data sources through local community expertise and global collaborations. Our students have worked with partners such as NYC Health + Hospitals, NYU Langone, Blue Cross Blue Shield, and Johnson & Johnson. Alongside rigorous academic publications, students engage in real-world projects that deliver measurable public health impact, and our graduates have a strong record of success with placements at organizations including Amazon, Meta, and UCSF, as well as recognition through awards like the Google PhD Fellowship. If you are interested in bringing data to life for tangible improvements in population health, CHDS offers a dynamic environment to learn, collaborate, and contribute.
The Attachment and Health Disparities Research Lab (AHDL)
The Attachment and Health Disparities Research Lab (AHDL) led by Dr. Stephanie Cook ,at NYU is a nationally recognized leader in examining how daily experiences in physical and digital environments shape stress, sleep, emotional wellbeing, and long term health. Our work combines spatial science, digital communication research, stress physiology, and responsible AI to identify how context becomes embedded in health processes and to design interventions that improve wellbeing at the individual and community levels. A defining feature of the lab is its validated training model that prepares students, postdoctoral fellows, and early career faculty to work across social science, advanced statistics, AI driven tools, spatial methods, and mixed methods inquiry. This integrated mentoring system is one of the lab’s most unique strengths. It produces scholars with rare interdisciplinary fluency and ensures that every major research project doubles as a training platform that builds future leaders who can responsibly and creatively solve the most pressing public health challenges of our time. Four students from the ADHL presented their research at the APHA conference in November, 2025.
The Biostatistical Collaboration and Consultation Core (BC3)
The Biostatistical Collaboration and Consultation Core (BC3), led by Dr. Alex Dahlen, is where statistical theory meets real-world research. We partner with clinical and public health investigators to design studies that balance scientific rigor with real-world constraints and to develop analysis plans that account for messy or biased data. Our work includes clinical trial design (adaptive, cluster-randomized, factorial), power calculations, causal inference with observational data, methods for missing data and measurement error, survival analysis, and mixed models for longitudinal and clustered data. We work with researchers throughout the full research process: from grant writing and study design through analysis, interpretation, and publication. Currently working with several investigators who are running clustered trials in hard-to-reach settings, as well as a few with adaptive / factorial design, though there is always a wide range of projects.
The Feng Lab
The Feng Lab at the NYU School of Global Public Health conducts methodological and theoretical research at the forefront of modern statistical learning, data science, and AI. Our group develops principled approaches for high-dimensional inference, network- and graph-structured data, nonparametric and semi-parametric modeling, and contemporary machine learning frameworks—including transfer learning, multi-task learning, and federated learning. We work closely with collaborators across medicine, genomics, epidemiology, neuroscience, and public health to translate methodological advances into impactful, domain‑driven applications. Our research philosophy emphasizes rigor, creativity, and cross‑disciplinary engagement. Trainees in the group contribute to the full spectrum of statistical science, including developing new theory, designing computationally efficient algorithms, analyzing large-scale biomedical data, and presenting their work at leading scientific venues. The lab is committed to cultivating an environment that values intellectual independence, collaboration, and professional development. The lab’s recent work has appeared in top statistics and machine learning journals, and recent trainees have gone on to secure tenure-track assistant professorships (PhD graduates) and admissions to competitive PhD programs (master’s graduates).
Dr. Heng’s Research Lab
Dr. Heng’s research focuses on causal inference methodology and its applications in public health, biomedical research, and social sciences. His overarching research agenda is to leverage advanced statistics and data science techniques (especially those concerning randomization-based inference, large-scale optimization, and machine learning) to remove or relax strong data assumptions in various causal inference settings. Some ongoing research projects include causal inference with treatment doses, randomized experiments with missing or error-prone data, and causal inference in inexactly matched observational studies, among others.
Dr. Mei’s Research Lab
Dr. Mei’s research interests are statistics, machine learning, and data science, and their applications in biomedical science, engineering, and public health. Currently his group’s methodology research focuses on public health surveillance, clinical trial design (e.g., dynamic borrowing, and sequential evaluation of efficacy and futility), and streaming data analysis (e.g., high-dimensional change-point detection and multi-armed bandit under the resources, sampling, or computing constraints). Dr. Mei has extensive and well-established experiences in mentoring students at various levels. Recent activities with master’s students include regular reading groups on reinforcement learning and participation in biostatistical consulting. His group seeks highly self-motivated students, regardless of whether their interests lie in theoretical, methodological, or applied research in biostatistics, epidemiology, machine learning, or data science.
Dr. Shu’s Research Lab
The Xu Quantitative Lab focuses on applying and evaluating innovative quantitative methods in social science and public health research. Our mission is to improve public health by inspiring innovative scholarship, practice, and leadership across disciplines. Our primary research track (though not limited to this area) involves tobacco use and health behavior change using data from the Population Assessment of Tobacco and Health (PATH) Study, with an emphasis on causal inference models, machine learning, latent growth models, and the development of statistical methods for longitudinal data analysis. We work to understand and address the health effects of tobacco use; assess the impact of tobacco use patterns on health outcomes; examine cessation and control strategies; evaluate effects across population subgroups; and assess tobacco campaigns and policies. We also conduct projects in psychometrics, health disparities, and health issues among minority groups. These projects are supported by funding from NIH institutes.
The Xu Quantitative Lab
The Xu Quantitative Lab focuses on applying and evaluating innovative quantitative methods in social science and public health research. Our mission is to improve public health by inspiring innovative scholarship, practice, and leadership across disciplines. Our primary research track (though not limited to this area) involves tobacco use and health behavior change using data from the Population Assessment of Tobacco and Health (PATH) Study, with an emphasis on causal inference models, machine learning, latent growth models, and the development of statistical methods for longitudinal data analysis. We work to understand and address the health effects of tobacco use; assess the impact of tobacco use patterns on health outcomes; examine cessation and control strategies; evaluate effects across population subgroups; and assess tobacco campaigns and policies. We also conduct projects in psychometrics, health disparities, and health issues among minority groups. These projects are supported by funding from NIH institutes.
Dr. Zhou’s Research Lab
My group's research is focused on developing theory and methods for network data modeling, high dimensional statistics, econometrics, machine learning, and causal inference; particularly with applications in genomics, genetics, bioinformatics, protein structure modeling, and political science. Ongoing research projects include modeling network data for academic collaborations, faculty hiring dynamics, polarization based on legislation; single cell RNA-seq analysis, integration, spatial transcriptome, and protein mutation. The current research is funded through grants from NSF and NIH.