Experimental Design When N Equals One
A Markovian framework for experimental design in N-of-1 trials and switchback experiments, optimizing treatment assignment to minimize estimation error of treatment effects.
The Causal Shift
Nonparametric Point Identification of Treatment Effect Distributions via Rank Stickiness
Identifying the entire treatment effect distribution via rank stickiness and Bregman-Sinkhorn copula. The conditional imputed outcome distribution is an exponential tilt of the marginal with a Bregman divergence as the exponent, yielding closed-form conditional moments and rank violation probabilities.
Gaussianized Design Optimization for Covariate Balance in Randomized Experiments
This paper presents Gaussianized Design Optimization, a novel framework for optimally balancing covariates in experimental design.
A Convexified Matching Approach to Imputation and Individualized Inference
We introduce a new convexified matching method for missing value imputation and individualized inference inspired by computational optimal transport.
Learning When the Concept Shifts: Confounding, Invariance, and Dimension Reduction
Confounding can obfuscate the definition of the best prediction model (concept shift) and shift covariates to domains yet unseen (covariate shift). Therefore, a model maximizing prediction accuracy in the source environment could suffer a significant accuracy drop in the target environment. We propose a new domain adaptation method for observational data in the presence of confounding, and characterize the the stability and predictability tradeoff leveraging a structural causal model.
Randomization Inference When N Equals One
A statistical theory for N-of-1 experiments, where a unit serves as its own control and treatment in rapid interleaving time windows.
Detecting Weak Distribution Shifts via Displacement Interpolation
Detecting weak, systematic distribution shifts and quantitatively modeling individual, heterogeneous responses to policies or incentives have found increasing empirical applications in social and economic sciences. We propose a model for weak distribution shifts via displacement interpolation, drawing from the optimal transport theory.
Blessings and Curses of Covariate Shifts: Adversarial Learning Dynamics, Directional Convergence, and Equilibria
Blessings and curses of covariate shifts, directional convergece, and the connection to experimental design.
Universal Prediction Band via Semi-Definite Programming
This paper proposes a computationally efficient method to construct nonparametric, heteroscedastic prediction bands for uncertainty quantification.
Deep Neural Networks for Estimation and Inference
Can deep neural networks with standard archtectures estimate treatment effects and perform downstream uncertainty quantification tasks?