★ Job market paper
Job Market Candidate · 2026–27
Ph.D. Candidate, Department of Economics
University of California, San Diego
h8wei@ucsd.edu
My work is on semiparametric inference — deriving efficiency bounds and influence functions, and building multiply robust estimators that attain them — for difference-in-differences, causal graphs, and off-policy evaluation.
Two literatures, one method. The three papers in the middle are where they meet.
hover a paper to see the topics it draws on
Hover or tap a title without a public link to see authors and abstract.
★ Job market paper
Staggered difference-in-differences designs face a control-group trade-off: using only never-treated units discards information, whereas imposing parallel trends against several untreated cohorts creates over-identifying restrictions and a different efficiency problem. We instead pool all not-yet-treated units into a sliding risk set and condition on the frozen pre-adoption history of each target cohort. The resulting sequential conditional-parallel-trends model accommodates dynamic selection through time-varying covariates and past outcomes while remaining exactly identified: apart from restrictions implied by the support of the outcome, it places no restriction on the observed data. We derive efficient influence functions for group-period and prespecified aggregate effects and propose a cross-fitted doubly robust one-step estimator and a pairwise targeted minimum loss-based estimator (TMLE) that updates each group-period target separately. The Horvitz–Thompson-normalized targeted estimator attains efficiency under a product-rate condition on the outcome-regression and inverse-risk-ratio errors, and a root-n bridge transfers the result to Hájek normalization under additional conditions. In a finite-support design, exact population calculations corroborate double-robust consistency, and the proposed one-step and pairwise targeted estimators show near-nominal Monte Carlo coverage at the largest sample size when at least one nuisance working model is correctly specified.
Exploiting the equality restrictions that nested Markov models encode requires their tangent-space geometry. For strictly positive finite-state models on arbitrary acyclic directed mixed graphs (ADMGs), we differentiate the recursive-head chart and prove that the range of its score map is the full tangent space. Intrinsic-set coordinate blocks form an algebraic direct sum, blocks of distinct districts are orthogonal, and the resulting Gram projection needs neither mb-shieldedness nor a district order. Exact counterexamples show that observational centering and kernel normalization alone do not certify tangency. For the node, complete-source edge, and compatible path-specific intervention targets considered here, boundary substitution yields a normalized configured active law and an order-free canonical-gradient formula, extended to finite mixtures by independent source redraws. A coherent one-step estimator with an exact remainder identity and a model-valid chart-flow targeted maximum likelihood estimator are efficient under stated local conditions. On a narrower source-isolated fixed-node subclass, a sequential estimator has an exact transition-factorized drift and up to 2m nuisance-correctness regimes over m active-district transitions; its all-correct influence function projects onto the canonical gradient, and an exact rational law exhibits a strict variance gap. These results separate order-free efficiency on arbitrary finite-state ADMGs from multiple robustness of a narrower construction.
Off-policy evaluation (OPE) constructs confidence intervals for the value of a target policy using data generated under a different behavior policy. Most existing inference methods focus on fixed target policies and may fail when the target policy is estimated as optimal, particularly when the optimal policy is non-unique or nearly deterministic. We study inference for the value of optimal policies in Markov decision processes. In an auxiliary augmented transition-sampling experiment, we characterize the existence of the efficient influence function and show that non-regularity arises when competing optimal policies have distinct first-order gradients. For the actual i.i.d.-trajectory experiment, we derive the semiparametric efficiency bound and a uniformly weighted estimator that attains it under a unique optimum, while the sequential NSAVE procedure trades efficiency for stability and validity under non-uniqueness. Motivated by this analysis, we propose a novel Nonparametric SequentiAl Value Evaluation (NSAVE) method, which yields martingale-based inference and retains a double-robustness property under policy-aligned nuisance estimation. We further develop a pointwise smoothing-based approximation under explicit first-stage rates, and a post-selection template with uniform coverage whenever its stated joint calibration condition is satisfied. Simulation studies support the theoretical results. An application to the Drink Less micro-randomized trial provides confidence intervals for state-adaptive notification policies and their improvement over the randomized behavior policy.
Causal mediation analysis is a powerful tool for disentangling the total effect of a treatment into its direct effect on the outcome and its indirect effect mediated through an intermediate variable. However, in observational studies, confounding between treatment and potential outcomes typically renders the total and natural effects non-identifiable. In this work, we advance mediation analysis within the difference-in-differences framework. Under a mediator-adjusted parallel trends assumption and additional conditions, we demonstrate that natural indirect, direct, and total effects are identifiable in the treated group. We further derive efficient influence functions for these estimands, enabling the construction of multiply robust and nonparametrically efficient estimators. We establish the asymptotic properties of these estimators. Applying our methodology to data from the Job Corps Study, we find that job training significantly increases both short-term and long-term earnings, after controlling for the indirect effect through the proportion of weeks employed.
During clinical trials evaluating a drug’s effect on a survival endpoint, intermediate events often occur in addition to the primary event. The treatment can exert its effect on the primary endpoint along multiple pathways through intermediate events. Assumptions for identifying mediation effects, such as sequential ignorability in natural effects or the dismissible components condition in separable effects, fail because intermediate events act as treatment-induced confounding. To understand the effect along each pathway, we consider hypothetical interventions in transitions between event statuses to mimic the treatment mechanism. The hypothetical interventions adjust for effects through intermediate events and marginalize over unobserved treatment-induced confounding, if any. Based on the derived efficient influence functions for the counterfactual cumulative incidences under hypothetical interventions, we construct multiply robust and semiparametrically efficient estimators for pathway treatment effects. Our proposed framework enables the examination of treatment effects through each transition, on each event, and along each path. By analyzing data from the LEADER Trial, we find that liraglutide significantly reduces the risk of cardiovascular and microvascular events. The reduction in all-cause mortality is primarily mediated by its effects on expanded major adverse cardiovascular events.
Identifying important features linked to a response variable is a fundamental task in various scientific domains. This article explores statistical inference for simulated Markov random fields in high-dimensional settings. We introduce a methodology based on Markov Chain Monte Carlo Maximum Likelihood Estimation (MCMC-MLE) with Elastic-net regularization. Under mild conditions on the MCMC method, our penalized MCMC-MLE method achieves ℓ₁-consistency. We propose a decorrelated score test, establishing both its asymptotic normality and that of a one-step estimator, along with the associated confidence interval. Furthermore, we construct two false discovery rate control procedures via the asymptotic behaviors for both p-values and e-values. Comprehensive numerical simulations confirm the theoretical validity of the proposed methods.
Many real-world bandit applications are characterized by sparse rewards, which can significantly hinder learning efficiency. Leveraging problem-specific structures for careful distribution modeling is recognized as essential for improving estimation efficiency in statistics. However, this approach remains under-explored in the context of bandits. To address this gap, we initiate the study of zero-inflated bandits, where the reward is modeled using a classic semi-parametric distribution known as the zero-inflated distribution. We develop algorithms based on the Upper Confidence Bound and Thompson Sampling frameworks for this specific structure. The superior empirical performance of these methods is demonstrated through extensive numerical studies.
Despite the great interest in the bandit problem, designing efficient algorithms for complex models remains challenging, as there is typically no analytical way to quantify uncertainty. In this paper, we propose Multiplier Bootstrap-based Exploration (MBE), a novel exploration strategy that is applicable to any reward model amenable to weighted loss minimization. We prove both instance-dependent and instance-independent rate-optimal regret bounds for MBE in sub-Gaussian multi-armed bandits. With extensive simulation and real data experiments, we show the generality and adaptivity of MBE.
Constant-specified and exponential concentration inequalities play an essential role in the finite-sample theory of machine learning and high-dimensional statistics. We obtain sharper and constants-specified concentration inequalities for the sum of independent sub-Weibull random variables, which leads to a mixture of two tails: sub-Gaussian for small deviations and sub-Weibull for large deviations from the mean. These bounds are new and improve existing bounds with sharper constants. In addition, a new sub-Weibull parameter is proposed, which enables recovering the tight concentration inequality for a random variable (vector). For statistical applications, we give an ℓ₂-error of estimated coefficients in negative binomial regressions when the heavy-tailed covariates are sub-Weibull distributed with sparse structures. In applying random matrices, we derive non-asymptotic versions of Bai–Yin’s theorem for sub-Weibull entries with exponential tail bounds. Finally, by demonstrating a sub-Weibull confidence region for a log-truncated Z-estimator without the second-moment condition, we discuss and define the sub-Weibull type robust estimator for independent observations without exponential-moment conditions.
This paper provides robust estimators and efficient inference of causal effects involving multiple interacting mediators. Most existing works either impose a linear model assumption among the mediators or are restricted to handle conditionally independent mediators given the exposure. To overcome these limitations, we define causal and individual mediation effects in a general setting, and employ a semiparametric framework to develop quadruply robust estimators for these causal effects. We further establish the asymptotic normality of the proposed estimators and prove their local semiparametric efficiencies. The proposed method is empirically validated via simulated and real datasets concerning psychiatric disorders in trauma survivors.
Tabular data in practice mix categorical and continuous variables. We model them with a tensor-spline CP decomposition — categorical variables enter as tensor modes and continuous ones through spline bases — so that a low-rank structure borrows strength across sparsely observed cells while keeping continuous effects smooth. We derive non-asymptotic error bounds for alternating least squares in both the rank-one and general-rank cases, and establish consistency for a Tucker-based simultaneous-diagonalization initializer that resolves the component-pairing problem before refinement.
Instructor of record
Fall 2026 · current
Associate-In, UC San Diego
Tutor
Ph.D. Econometrics Qualifying Exam
Teaching assistant
Led discussion and review sessions, held weekly office hours, assisted in preparing exams and problem sets, and graded exams and assignments.
Econometrics 220C
Advanced Multivariate Statistical Analysis
Asymptotic Statistics
Econometrics 120B and 120C
Economic & Business Forecasting
Time Series
Probability and Statistics for Engineers
Introduction to Survey Sampling & Statistical Methods for Quality and Productivity Improvement