Featured Publications

The advent and subsequent widespread availability of preventive vaccines has altered the course of public health over the past century. Despite this success, effective vaccines to prevent many high-burden diseases, including HIV, have been slow to develop. Vaccine development can be aided by the identification of immune response markers that serve as effective surrogates for clinically significant infection or disease endpoints. However, measuring immune response is often costly, which has motivated the usage of two-phase sampling for immune response sampling in clinical trials of preventive vaccines. In such trials, measurement of immunological markers is performed on a subset of trial participants, where enrollment in this second phase is potentially contingent on the observed study outcome and other participant-level information. We propose nonparametric methodology for efficiently estimating a counterfactual parameter that quantifies the impact of a given immune response marker on the subsequent probability of infection. Along the way, we fill in a theoretical gap pertaining to the asymptotic behavior of nonparametric efficient estimators in the context of two-phase sampling, including a multiple robustness property enjoyed by our estimators. Techniques for constructing confidence intervals and hypothesis tests are presented, and an open source software implementation of the methodology, the txshift R package, is introduced. We illustrate the proposed techniques using data from a recent preventive HIV vaccine efficacy trial.
Preprint Code Project Slides
I Díaz, NS Hejazi
In Journal of the Royal Statistical Society, Series B (Statistical Methodology)

Mediation analysis in causal inference has traditionally focused on binary treatment regimes and deterministic interventions, as well as a decomposition of the average treatment effect in terms of direct and indirect effects. In this paper we present an analogous decomposition of the population intervention effect, defined through stochastic interventions. Population intervention effects provide a generalized framework in which a variety of interesting causal contrasts can be defined, including effects for continuous and categorical exposures. We show that identification of direct and indirect effects for the population intervention effect requires weaker assumptions than its average treatment effect counterpart. In particular, identification of direct effects is guaranteed in experiments that randomize the treatment and the mediator. We discuss various estimators of the direct and indirect effects, including substitution, re-weighted, and efficient estimators based on flexible regression techniques. Our efficient estimator is asymptotically linear under a condition requiring $n^{\frac{1}{4}}$-consistency of certain regression functions. We perform a simulation study in which we assess the finite-sample properties of our proposed estimators. We present the results of an illustrative study where we assess the effect of participation in a sports team on BMI among children, using mediators such as exercise habits, daily consumption of snacks, and overweight status.
Preprint PDF Code Project Project

Interventional effects for mediation analysis were proposed as a solution to the lack of identifiability of natural (in)direct effects in the presence of a mediator-outcome confounder affected by exposure. We present a theoretical and computational study of the properties of the interventional (in)direct effect estimands based on the efficiency bound in the non-parametric statistical model. We derive the efficient influence function, using it to develop two asymptotically optimal, non-parametric estimators that leverage data-adaptive regression for estimation of the nuisance parameters: a one-step estimator and a targeted minimum loss estimator. A free and open source R package implementing our proposed estimators is made readily available on GitHub. We further present results establishing the conditions under which these estimators are consistent, rate multiply robust, $n^{\frac{1}{2}}$-consistent and efficient. We illustrate the finite-sample performance of the estimators and corroborate our theoretical results in a simulation study. We also demonstrate the use of the estimators in our motivating application to elucidate the mechanisms behind the unintended harmful effects that a housing intervention had on adolescent girls’ risk behavior.
Preprint Code Project

Recent Publications

(see CV for a full list)

Quickly discover relevant content by filtering publications.

(2020). Nonparametric inverse probability weighted estimators based on the highly adaptive lasso.

Preprint Project

(2020). Efficient nonparametric inference on the effects of stochastic interventions under two-phase sampling, with applications to vaccine efficacy trials.

Preprint Code Project Slides

(2020). Exploring high-dimensional biological data with sparse contrastive principal component analysis. In Bioinformatics.

Preprint PDF Code Project

(2020). scPCA: A toolbox for sparse contrastive principal component analysis in R. In Journal of Open Source Software.

PDF Code Project Source Document

(2020). Causal mediation analysis for stochastic interventions. In Journal of the Royal Statistical Society, Series B (Statistical Methodology).

Preprint PDF Code Project Project

See all publications

Recent & Upcoming Talks

Wed, Apr 29, 2020 1:30 PM Berkeley, California, United States
Tue, Jun 25, 2019 11:00 AM New York, New York, United States
Thu, Mar 21, 2019 3:00 PM Berkeley, California, United States
Fri, Sep 14, 2018 10:00 AM Berkeley, California, United States
Thu, Aug 2, 2018 8:30 AM Vancouver, British Columbia, Canada
See all talks

Teaching

current courses

  • None for now. Check back later.

past courses

recent workshops

Carpentries workshops

I am an active member of Software Carpentry and Data Carpentry, through which I work on curriculum development, maintenance of lesson materials, and workshop delivery.

Software

Collected collateral damage from doing statistics research, hopefully useful to others.

Targeted Learning and the tlverse

The tlverse is an ecosystem of R packages for Targeted Learning, of which I am a co-founder and core developer. A few of the tlverse packages to which I have made significant contributions include

  • sl3: An R package providing a modern implementation of the Super Learner ensemble modeling algorithm that simultaneously exposes a grammar for composing arbitrary pipelines for machine learning. Joint work with Jeremy Coyle, Ivana Malenica, and Oleg Sofrygin.
    [Docs] | [GitHub]

  • origami: An R package exposing a generalized framework for the application of a variety of cross-validation schemes to arbitrary functions, facilitating the extension of cross-validation to (and its use in) a diversity of applications. Joint work with Jeremy Coyle.
    [Docs] | [GitHub] | [CRAN]

  • hal9001: An R package providing an efficient implementation of the Highly Adaptive Lasso (HAL), a nonparametric regression estimator with fast convergence guarantees under mild assumptions. Joint work with Jeremy Coyle and Mark van der Laan.
    [Docs] | [GitHub] | [CRAN]

  • tmle3shift: An R package providing a targeted maximum likelihood estimator(s) for the causal effects of modified treatment policies on continuous-valued exposures. Incorporates nonparametric working marginal structural models for summarization of effect estimates. Joint work with Jeremy Coyle and Mark van der Laan.
    [Docs] | [GitHub]

Causal Inference with Machine Learning

A significant focus of my research program lies at the intersection of causal inference and statistical machine learning. I’ve (co-)developed R packages for settings ranging from causal mediation analysis and the assessment of stochastic intervention effects with two-phase sampling to nonparametric conditional density estimation and survival analysis.

  • medshift: An R package for estimating the population intervention (in)direct effects based on stochastic interventions. Classical and efficient estimators are supported for the effects of incremental propensity score interventions and modified treatment policies. Joint work with Iván Díaz.
    [Docs] | [GitHub]

  • medoutcon: An R package for the efficient estimation of stochastic interventional (in)direct effects identifiable under intermediate confounding, including one-step and targeted minimum loss estimators. Joint work with Iván Díaz and Kara Rudolph.
    [Docs] | [GitHub]

  • txshift: An R package for efficient estimation of and inference on causal effects of stochastic interventions on continuous-valued exposures. Robust estimation and efficient inference under two-phased sampling is supported. Joint work with David Benkeser.
    [Docs] | [GitHub]

  • haldensify: An R package for nonparametric conditional density estimation using techniques based on the highly adaptive lasso, designed primarily for estimation of the generalized propensity score. Joint work with David Benkeser and Mark van der Laan.
    [Docs] | [GitHub] | [CRAN]

  • survtmle: An R package for the construction of targeted maximum likelihood estimates of marginal cumulative incidence in survival settings with and without competing risks, including estimation procedures that respect bounds. Joint work with David Benkeser.
    [Docs] | [GitHub] | [CRAN]

Computational Biology and Bioconductor

A parallel thread of my research concerns the development of novel statistical methodologies for application in high-dimensional and computational biology settings. Consequently, I have (co-)developed several R packages extending the Bioconductor Project.

Miscellaneous

Projects

*
All Causal Inference Biostatistics Targeted Learning Miscellany

Efficient estimation of functional target parameters based on the highly adaptive lasso minimum loss estimator (HAL-MLE).

Cross-validated selection; robust, sparsified estimation; and dimension reduction for high-dimensional (contrastive) covariance matrices.

Defining novel, more flexible causal effects for mediation analysis, primarily using the formalism of stochastic interventions.

Estimating the causal effects of stochastic treatment regimes, including conditional density estimation and two-phase sampling corrections.

Introducing empirical Bayes variance moderation for data adaptive variable importance in high-dimensional biology applications.

The things that keep me from working.

Assorted notes on graduate school.

Contact