Nicole Pashley
Rutgers University-New Brunswick, NJ·Mathematics & Statistics
To learn whether a treatment, program or policy actually works, researchers often run experiments in several schools, clinics or towns at once. These units are called sites or blocks.
- Fields
Mathematics & Statistics
Social Science
- Topics
causal inference
randomization-based inference
randomized controlled trials
- Grants
- 1 known grant, through Jul 2027
What they work on
- Develop randomization-based methods to analyze incomplete block designs, where each site runs only a random subset of the treatments, using the potential outcomes framework that relies on fewer assumptions than model-based approaches.
- Determine which causal effects can be identified in multisite factorial experiments when some sites lack information on certain factors or did not randomize them, and develop techniques to estimate those effects.
- Identify when variation in treatment effects across sites can be learned from blocked and multisite experiments, and develop ways to measure this variation.
- Release freely available statistical software implementing the new methods, and use project materials to build an undergraduate causal inference course.
More about the research
Each site runs its own small randomized experiment. These designs are common in the social and behavioral sciences, but the statistical tools for analyzing them have important gaps. This is especially true for tools that rely only on the random assignment itself rather than on assumed statistical models.
Why it matters
Social and behavioral scientists who run experiments with people need analysis tools that do not depend on modeling assumptions that may not fit their data. These methods could give more reliable answers from multisite trials. Measuring how much effects vary across sites could also help decision-makers judge whether a program or policy should be expanded to a large scale.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Alyssa Carlson
University of Missouri-Columbia, MO·Social Science·Early-career
Establish identification in triangular random coefficient models with continuous endogenous variables using a general control function that does not require scalar heterogeneity, the assumption of a single hidden first-stage factor.
Caleb Miles
Columbia University, NY·Mathematics & Statistics
Develop simple parametric and semiparametric efficient estimators of the average treatment effect in multi-study, multi-outcome data fusion, using related follow-up measurements as proxies for outcomes missing in some trials.
Matias Cattaneo
Princeton University, NJ·Mathematics & Statistics
Demonstrate the empirical and theoretical limitations of binned regression models applied to mixed-frequency panel data in climate economics, showing when they can lead to incorrect conclusions.
The school
Rutgers University-New Brunswick: 57 labs on PI Pages, $837M a year on research, 713 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.