Skip to main content

Search NYU Steinhardt

Image of Professor Hill outdoors.

Jennifer Hill

Professor of Applied Statistics; Co-Department Chair; Co-Director of PRIISM

Applied Statistics, Social Science, and Humanities

(please use email)

Jennifer Hill develops and evaluates methods to help answer the types of causal questions that are vital to policy research and scientific development. In particular she focuses on situations in which it is difficult or impossible to perform traditional randomized experiments, or when even seemingly pristine study designs are complicated by missing data or hierarchically structured data. Most recently Hill has been pursuing two intersecting strands of research. The first focuses on Bayesian nonparametric methods that allow for flexible estimation of causal models and are less time-consuming and more precise than competing methods (e.g. propensity score approaches). The second line of work pursues strategies for exploring the impact of violations of typical causal inference assumptions such as ignorability (all confounders measured) and common support (overlap). Hill has published in a variety of leading journals including Journal of the American Statistical Association, Statistical Science, American Political Science Review, American Journal of Public Health, and Developmental Psychology. Hill earned her PhD in Statistics at Harvard University in 2000 and completed a post-doctoral fellowship in Child and Family Policy at Columbia University's School of Social Work in 2002.

Hill is currently the Co-Chair of the Department of Applied Statistics, Social Science, and Humanities (ASH) Department as well as  the Co-Director of the Center for Practice and Research at the Intersection of Information, Society, and Methodology (PRIISM). She was the co-founder of the Master's of Science Program in Applied Statistics for Social Science Research (A3SR). The A3SR program has concentration in Data Science for Social Impact. As far as we know this is the first degree granting program in Statistics or Data Science for Social Impact or Social Good in the world. The A3SR program also has a dual degree option with the MPA program at the Wagner School that allows students  to earn both degrees in two years.

In 2021, Jennifer Hill was awarded the New York University Distinguished Teaching Award.

To hear more about Hill's perspective on causal inference watch her interview on the SuperDataScience podcast. Out of the 104 episodes recorded in 2022, Hill's was the 2nd most popular.

Hill is excited to share the new software she is developing for machine-learning-based causal inference, thinkCausal, that has an easy-to-use interface and allows users to learn while they use the software. It can be accessed here.

Selected Publications

Check out my recent interview about Causal Inference on the SuperDataScience podcast! You can find it here: www.superdatascience.com/607

  • Dorie, Vincent, George Perrett, Jennifer L. Hill, and Benjamin Goodrich (2022) “Stan and BART for Causal Inference: Estimating Heterogeneous Treatment Effects Using the Power of Stan and the Flexibility of Machine Learning,” Entropy, 24(12): 1782.
  • Harel, D., Seaman, D., Hill, J., King, E., and D. Burde (2022) “The impact of indirect questioning: Asking about you versus your friends,” International Journal of Social Research Methodology, (accepted)
  • Gaebler, J., Cai, W., Basse, G., Shroff, R., Goel, and S. and J. Hill (2022) “A causal framework for observational studies of discrimination,” Statistics and Public Policy, 9:1, 26-48.
  • Whipps, M., Yoshikawa, H., Demirci, J., and J. Hill (2022) “Painful, yet beautiful, moments: Pathways through Infant Feeding and Dynamic Conceptions of Breastfeeding Success,” in press at Qualitative Health Research, 32(1): 31-47
  • Whipps, M., Yoshikawa, H., Demirci, J., and J. Hill (2021) “Estimating the Impact of In-Hospital Infant Formula Supplementation on Breastfeeding Success,” Breastfeeding Medicine, 16(7): 530-538, https://doi.org/10.1089/bfm.2020.0194
  • Benway, N., Hitchcock, E.R., McAllister, T., Feeny, G.T., Hill, J., and J. Preston (2021) “Comparing biofeedback types for children with residual /ɹ/ errors in American English: A single case randomization design,” American Journal of Speech-Language Pathology, 30(4): 1819-1845
  • Reinstein, I., Hill, J., Cook, D., Lineberry, M., and M. Pusic (2021) “Multi-level longitudinal learning curve regression models integrated with item difficulty metrics for deliberate practice of visual diagnosis: groundwork for adaptive learning,” Advances in Health Sciences Education https://doi.org/10.1007/s10459-021-10027-0
  • Gelman, A. and J. Hill (2020) Regression and Other Stories, Cambridge University Press.
  • Hill, J., Linero, A., and J. Murray (2020) “Bayesian Additive Regression Trees: A Review and Look Forward,” Annual Review of Statistics and Its Application, 7: 251-278.
  • Dorie, V., Hill, J., Shalit, U., Scott, M. and D. Cervone (2019) “Automated versus do-it-yourself methods for causal inference: Lessons learned from a data analysis competition,” Statistical Science (with commentary and rejoinder), 34(1): 43:68, 94-99.
  • Scott, M., Diakow, R., Hill, J. and J. Middleton (2018) “Potential for Bias Inflation with Grouped Data:  A Comparison of Estimators and a Sensitivity Analysis Strategy,” Observational Studies, 4: 111-149.
  • Kern, H., Stuart, E., Hill, J. and D. Green (2016) “Assessing methods for generalizing experimental impact estimates to target samples,” Journal of Research in Educational Effectiveness, 9(1): 103-127.
  • Middleton, J., Scott, M., Diakow, R. and J. Hill (2016) “Bias Amplification and Bias Unmasking” Political Analysis, 24(3): 307-323. (Winner of Society for Political Methodology's Miller Prize for the best article appearing in Political Analysis in 2016)
  • Hill, J. and Y. Su (2013) “Assessing lack of common support in causal inference using Bayesian nonparametrics: implications for evaluating the effect of breastfeeding on children's cognitive outcomes,” Annals of Applied Statistics, 7(3): 1386-1420.
  • Hill, J. (2011) “Bayesian nonparametric modeling for causal inference,” Journal of Computational and Graphical Statistics, 20(1): 217-240.

Courses

Causal Inference

Course provides students with a basic knowledge of both how to perform analyses and critique the use of some more advanced statistical methods useful in answering policy questions. While randomized experiments will be discussed, the primary focus will be the challenge of answering causal questions using data that do not meet such standards. Several approaches for observational data including propensity score methods, instrumental variables, difference in differences, fixed effects models and regression discontinuity designs will be discussed. Examples from real public policy studies will be used to illustrate key ideas and methods.
Course #
APSTA-GE 2012
Credits
3
Department
Applied Statistics, Social Science, and Humanities

Data Science for Social Impact

Course focuses on the competencies required and the issues that arise Course focuses on how analysts use data and quantitative evidence to impact policy and practice. Students will learn how to gather and analyze data to address questions about program efficacy and efficient targeting of resources. Topics will include how to choose organizational partners, implement change, build trust with organizations and civic agencies, satisfy the needs of stakeholders and manage legal, ethical, and logistical constraints. Students will discuss real case studies and appropriate ways to address them.
Course #
APSTA-GE 2331
Credits
3
Department
Applied Statistics, Social Science, and Humanities

Data Science Translation: Writing, Speaking, and Visualization

The goal of this course is to learn how to effectively, honestly, and persuasively communicate about empirical research. Students develop competencies in writing, visualization, and oral presentation of technical material to both technical and lay audiences. Students learn practical strategies with ample opportunity to practice new skills. Assignments and discussion emphasize and explore the tension between concision and accuracy. Students receive feedback from the instructor, peers, and exemplars of intended audiences (e.g. employers who hire data scientists).
Course #
APSTA-GE 2355
Credits
3
Department
Applied Statistics, Social Science, and Humanities

Missing Data

Course provides students with a basic knowledge of missing data analysis, beginning with the types of missing data mechanisms (e.g., missing completely at random). We then discuss the problems with ignoring missing data and examine problems with conventional fixes. Single imputation with noise is contrasted with multiple imputation approaches. Real examples from policy research are given throughout. More advanced topics include pattern mixture models and handling data that are not missing at random.
Course #
APSTA-GE 2013
Credits
2
Department
Applied Statistics, Social Science, and Humanities

Statistical Consulting Research Seminar

This course is designed to assist graduate students in the quantitative methods specific to the design and analysis of their theses. In this seminar format, under the guidance of one or more statistical faculty members, students will have opportunity to present and defend their scholarly work-in-progress. They will also be required to critique and provide constructive suggestions for their fellow students. The focus of critiques will be on the research methodology and other statistical issues. Students will additionally benefit from being able to observe how the participating faculty diagnosis and solve statistical issues that arise in others' presented work and to benefit from this advice in their own work. In essence this course provides training in statistical consulting along with detailed feedback on one's dissertation research
Course #
APSTA-GE 2401
Credits
3
Department
Applied Statistics, Social Science, and Humanities

Statistical Mysteries and How to Solve Them

An introductory quantitative and statistical reasoning course designed to help students acquire statistical literacy and competency to survive in a data-rich world. The course introduces students to basic concepts in probability, research design, descriptive statistics, and simple predictive models to help them to become more savvy consumers of the information they will routinely be exposed to in their personal, academic and professional lives. Course material will be conveyed through video clips, case studies, puzzle solving, predictive competitions, and group discussions.

Liberal Arts Core/CORE Equivalent - satisfies the requirement for Quantitative Reasoning for certain programs; students should check with their Academic Advisor for confirmation.
Course #
APSTA-UE 10
Credits
4
Department
Applied Statistics, Social Science, and Humanities
Liberal Arts Core
Quantitative Reasoning