Methodological research has focused on the development of methods for causal inference, especially causal mediation analysis (e.g., Dı́az et al., 2020; Hejazi et al., 2023b); causal (or de-biased) machine learning (e.g., Ertefaie et al., 2023); semi-parametric corrections for efficient estimation with auxiliary- or outcome-dependent, two-phase sampling designs (Hejazi et al., 2021a); and applying flexible intervention schemes when the assumption of non-interference between units breaks down (Balkus et al., 2025).
Other areas of focus have varied widely, including causal inference procedures for identifying biomarkers and assessing effect modification from high-dimensional biology data (Hejazi et al., 2023a; Boileau et al., 2025); causal survival analysis in settings wtih competing risks (Dı́az et al., 2024); asymptotically optimal loss-based estimator selection for covariance matrix estimation in high-dimensional settings (Boileau et al., 2023); and causal segment discovery within large-scale digital experiments (Hejazi et al., 2021b).
selected publications
Some representative publications appear below. Please consult Google Scholar or a recent CV for a comprehensive list. Below, the names of group members appear in bold, including those of trainees and of the PI; the names of frequent collaborators are italicized and underlined.
Balkus, S.V., Delaney, S. and
Hejazi, N.S. (2025)
The causal effects of modified treatment policies under network interference.
revision invited at Journal of the Royal Statistical Society, Series B: Statistical Methodology.
Boileau, P.,
Hejazi, N.S.,
van der Laan, M.J. and Dudoit, S. (2023)
Cross-validated loss-based covariance matrix estimator selection in high dimensions.
Journal of Computational and Graphical Statistics,
32, 601–612.
Boileau, P., Leng, N.,
Hejazi, N.S.,
van der Laan, M.J. and Dudoit, S. (2025)
A nonparametric framework for treatment effect modifier discovery in high dimensions.
Journal of the Royal Statistical Society, Series B: Statistical Methodology,
87, 157–185.
Dı́az, I. and
Hejazi, N.S. (2020)
Causal mediation analysis for stochastic interventions.
Journal of the Royal Statistical Society, Series B: Statistical Methodology,
82, 661–683.
Dı́az, I.,
Hejazi, N.S., Rudolph, K.E. and
van der Laan, M.J. (2021)
Non-parametric efficient causal mediation with intermediate confounders.
Biometrika,
108, 627–641.
Dı́az, I., Williams, N.T., Hoffman, K.L. and
Hejazi, N.S. (2024)
Causal survival analysis under competing risks using longitudinal modified treatment policies.
Lifetime Data Analysis,
30, 213–236.
Hejazi, N.S.,
Boileau, P.,
van der Laan, M.J. and
Hubbard, A.E. (2023a)
A generalization of moderated statistics to data adaptive semiparametric estimation in high-dimensional biology.
Statistical Methods in Medical Research,
32, 539–554.
Hejazi, N.S., Rudolph, K.E.,
van der Laan, M.J. and
Dı́az, I. (2023b)
Nonparametric causal mediation analysis for stochastic interventional (in)direct effects.
Biostatistics,
24, 686–707.
Hejazi, N.S.,
van der Laan, M.J., Janes, H.E.,
Gilbert, P.B. and Benkeser, D.C. (2021a)
Efficient nonparametric inference on the effects of stochastic interventions under two-phase sampling, with applications to vaccine efficacy trials.
Biometrics,
77, 1241–1253.
Hejazi, N.S., Zheng, W. and Anand, S. (2021b)
A framework for causal segmentation analysis with machine learning in large-scale digital experiments.
Conference on Digital Experimentation at MIT,
8th (annual).