Oliver Dukes
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Oliver Dukes has a total of 45 co-authors. Here are the top co-authors by number of shared publications:
- Stijn Vansteelandt
Department of Mathematics, Computer Science and Statistics, Ghent University
7 shared publications - Kelly Van Lancker
Department of Mathematics, Computer Science and Statistics, Ghent University
3 shared publications - Lin Liu
Shanghai Jiao Tong University
3 shared publications - Linbo Wang
Department of Statistical Sciences, University of Toronto , Toronto
3 shared publications - Avi Feller
University of California, Berkeley, CA, USA
2 shared publications David Bruns-Smith
Graduate School of Business, Stanford University , Stanford, CA
2 shared publications
Latest Publications
- 9 April 2026
- Published by Oxford University Press (OUP) in Biometrics
- Vol. 82 (2)
Discussion on ‘‘Nonparanormal Adjusted Marginal Inference’’ by Susanne Dandl and Torsten Hothorn
We comment on the work of Dandl and Hothorn, who propose Nonparanormal Adjusted Marginal Inference, a covariate-adjusted method for estimating marginal treatment effects in randomized studies. We discuss their likelihood-based inferential strategy for parameterizing and estimating marginal contrasts and compare this fully parametric approach with established semiparametric methods. We then critically assess its robustness and practical suitability for routine use in clinical trials.
- 9 April 2026
- Published by Oxford University Press (OUP) in Biometrics
- Vol. 82 (2)
Discussion on ‘‘Nonparanormal Adjusted Marginal Inference’’ by Susanne Dandl and Torsten Hothorn
We comment on the work of Dandl and Hothorn, who propose Nonparanormal Adjusted Marginal Inference, a covariate-adjusted method for estimating marginal treatment effects in randomized studies. We discuss their likelihood-based inferential strategy for parameterizing and estimating marginal contrasts and compare this fully parametric approach with established semiparametric methods. We then critically assess its robustness and practical suitability for routine use in clinical trials.
- Top Cited PapersOpen Access
- 24 April 2025
- Published by Oxford University Press (OUP) in Journal of the Royal Statistical Society Series B: Statistical Methodology
- Vol. 88 (3) , 699-723
Augmented balancing weights as linear regression
We provide a novel characterization of augmented balancing weights, also known as automatic debiased machine learning. These popular doubly robust estimators combine outcome modelling with balancing weights—weights that achieve covariate balance directly instead of estimating and inverting the propensity score. When the outcome and weighting models are both linear in some (possibly infinite) basis, we show that the augmented estimator is equivalent to a single linear model with coefficients that combine those of the original outcome model with those from unpenalized ordinary least-squares (OLS). Under certain choices of regularization parameters, the augmented estimator in fact collapses to the OLS estimator alone. We then extend these results to specific outcome and weighting models. We first show that the augmented estimator that uses (kernel) ridge regression for both outcome and weighting models is equivalent to a single, undersmoothed (kernel) ridge regression—implying a novel analysis of undersmoothing. When the weighting model is instead lasso-penalized, we demonstrate a familiar ‘double selection’ property. Our framework opens the black box on this increasingly popular class of estimators, bridges the gap between existing results on the semiparametric efficiency of undersmoothed and doubly robust estimators, and provides new insights into the performance of augmented balancing weights.
- 24 April 2025
- Published by Oxford University Press (OUP) in Journal of the Royal Statistical Society Series B: Statistical Methodology
- Vol. 88 (3) , 699-723
Top Cited PapersOpen AccessAugmented balancing weights as linear regression
We provide a novel characterization of augmented balancing weights, also known as automatic debiased machine learning. These popular doubly robust estimators combine outcome modelling with balancing weights—weights that achieve covariate balance directly instead of estimating and inverting the propensity score. When the outcome and weighting models are both linear in some (possibly infinite) basis, we show that the augmented estimator is equivalent to a single linear model with coefficients that combine those of the original outcome model with those from unpenalized ordinary least-squares (OLS). Under certain choices of regularization parameters, the augmented estimator in fact collapses to the OLS estimator alone. We then extend these results to specific outcome and weighting models. We first show that the augmented estimator that uses (kernel) ridge regression for both outcome and weighting models is equivalent to a single, undersmoothed (kernel) ridge regression—implying a novel analysis of undersmoothing. When the weighting model is instead lasso-penalized, we demonstrate a familiar ‘double selection’ property. Our framework opens the black box on this increasingly popular class of estimators, bridges the gap between existing results on the semiparametric efficiency of undersmoothed and doubly robust estimators, and provides new insights into the performance of augmented balancing weights.
- 12 April 2025
- Published by Oxford University Press (OUP) in International Journal of Epidemiology
- Vol. 54 (3)
Change scores and baseline adjustment: splitting the difference (in differences)
A lively debate exists on how best to incorporate repeated measurements of an outcome in a statistical analysis. Two popular approaches are change-score analyses (the difference in baseline and follow-up outcome measurements are regressed on the exposure) and baseline adjustment (in which baseline outcomes are included as a covariate in a regression model). In this article, we compare both through the lens of the causal inference literature. We draw in particular on the connections between change-score analyses and ‘difference-in-differences’—a popular approach for inferring causal effects in economics and social sciences, which has received less attention in epidemiology. We make practical recommendations for which approach to use, based on one’s knowledge or belief about the confounding mechanism.
- 12 April 2025
- Published by Oxford University Press (OUP) in International Journal of Epidemiology
- Vol. 54 (3)
Change scores and baseline adjustment: splitting the difference (in differences)
A lively debate exists on how best to incorporate repeated measurements of an outcome in a statistical analysis. Two popular approaches are change-score analyses (the difference in baseline and follow-up outcome measurements are regressed on the exposure) and baseline adjustment (in which baseline outcomes are included as a covariate in a regression model). In this article, we compare both through the lens of the causal inference literature. We draw in particular on the connections between change-score analyses and ‘difference-in-differences’—a popular approach for inferring causal effects in economics and social sciences, which has received less attention in epidemiology. We make practical recommendations for which approach to use, based on one’s knowledge or belief about the confounding mechanism.
- 22 November 2024
- Published by Oxford University Press (OUP) in Biometrika
- Vol. 112 (1) , asae064
Using negative controls to identify causal effects with invalid instrumental variables
Summary: Many proposals for the identification of causal effects require an instrumental variable that satisfies strong, untestable unconfoundedness and exclusion restriction assumptions. In this paper, we show how one can potentially identify causal effects under violations of these assumptions by harnessing a negative control population or outcome. This strategy allows one to leverage subpopulations for whom the exposure is degenerate, and requires that the instrument-outcome association satisfies a certain parallel trend condition. We develop semiparametric efficiency theory for a general instrumental variable model, and obtain a multiply robust, locally efficient estimator of the average treatment effect in the treated. The utility of the estimators is demonstrated in simulation studies and an analysis of the Life Span Study.
- 22 November 2024
- Published by Oxford University Press (OUP) in Biometrika
- Vol. 112 (1) , asae064
Using negative controls to identify causal effects with invalid instrumental variables
Summary: Many proposals for the identification of causal effects require an instrumental variable that satisfies strong, untestable unconfoundedness and exclusion restriction assumptions. In this paper, we show how one can potentially identify causal effects under violations of these assumptions by harnessing a negative control population or outcome. This strategy allows one to leverage subpopulations for whom the exposure is degenerate, and requires that the instrument-outcome association satisfies a certain parallel trend condition. We develop semiparametric efficiency theory for a general instrumental variable model, and obtain a multiply robust, locally efficient estimator of the average treatment effect in the treated. The utility of the estimators is demonstrated in simulation studies and an analysis of the Life Span Study.
- 22 June 2023
- Published by Oxford University Press (OUP) in Biometrics
- Vol. 79 (4) , 3096-3110
Ensuring Valid Inference for Cox Hazard Ratios After Variable Selection
The problem of how to best select variables for confounding adjustment forms one of the key challenges in the evaluation of exposure effects in observational studies, and has been the subject of vigorous recent activity in causal inference. A major drawback of routine procedures is that there is no finite sample size at which they are guaranteed to deliver exposure effect estimators and associated confidence intervals with adequate performance. In this work, we will consider this problem when inferring conditional causal hazard ratios from observational studies under the assumption of no unmeasured confounding. The major complication that we face with survival data is that the key confounding variables may not be those that explain the censoring mechanism. In this paper, we overcome this problem using a novel and simple procedure that can be implemented using off-the-shelf software for penalized Cox regression. In particular, we will propose tests of the null hypothesis that the exposure has no effect on the considered survival endpoint, which are uniformly valid under standard sparsity conditions. Simulation results show that the proposed methods yield valid inferences even when covariates are high-dimensional.
- 22 June 2023
- Published by Oxford University Press (OUP) in Biometrics
- Vol. 79 (4) , 3096-3110
Ensuring Valid Inference for Cox Hazard Ratios After Variable Selection
The problem of how to best select variables for confounding adjustment forms one of the key challenges in the evaluation of exposure effects in observational studies, and has been the subject of vigorous recent activity in causal inference. A major drawback of routine procedures is that there is no finite sample size at which they are guaranteed to deliver exposure effect estimators and associated confidence intervals with adequate performance. In this work, we will consider this problem when inferring conditional causal hazard ratios from observational studies under the assumption of no unmeasured confounding. The major complication that we face with survival data is that the key confounding variables may not be those that explain the censoring mechanism. In this paper, we overcome this problem using a novel and simple procedure that can be implemented using off-the-shelf software for penalized Cox regression. In particular, we will propose tests of the null hypothesis that the exposure has no effect on the considered survival endpoint, which are uniformly valid under standard sparsity conditions. Simulation results show that the proposed methods yield valid inferences even when covariates are high-dimensional.
- Open Access
- 20 June 2023
- Published by Oxford University Press (OUP) in American Journal of Epidemiology
- Vol. 192 (10) , 1772-1780
Estimating the Effect of a Treatment When There Is Nonadherence in a Trial
Randomized trials offer a powerful strategy for estimating the effect of a treatment on an outcome. However, interpretation of trial results can be complicated when study subjects do not take the treatment to which they were assigned; this is referred to as nonadherence. Prior authors have described instrumental variable approaches to analyze trial data with nonadherence; under their approaches, the initial assignment to treatment is used as an instrument. However, their approaches require the assumption that initial assignment to treatment has no direct effect on the outcome except via the actual treatment received (i.e., the exclusion restriction), which may be implausible. We propose an approach to identification of a causal effect of treatment in a trial with 1-sided nonadherence without assuming exclusion restriction. The proposed approach leverages the study subjects initially assigned to control status as an unexposed reference population; we then employ a bespoke instrumental variable analysis, where the key assumption is “partial exchangeability” of the association between a covariate and an outcome in the treatment and control arms. We provide a formal description of the conditions for identification of causal effects, illustrate the method using simulations, and provide an empirical application.
- 20 June 2023
- Published by Oxford University Press (OUP) in American Journal of Epidemiology
- Vol. 192 (10) , 1772-1780
Open AccessEstimating the Effect of a Treatment When There Is Nonadherence in a Trial
Randomized trials offer a powerful strategy for estimating the effect of a treatment on an outcome. However, interpretation of trial results can be complicated when study subjects do not take the treatment to which they were assigned; this is referred to as nonadherence. Prior authors have described instrumental variable approaches to analyze trial data with nonadherence; under their approaches, the initial assignment to treatment is used as an instrument. However, their approaches require the assumption that initial assignment to treatment has no direct effect on the outcome except via the actual treatment received (i.e., the exclusion restriction), which may be implausible. We propose an approach to identification of a causal effect of treatment in a trial with 1-sided nonadherence without assuming exclusion restriction. The proposed approach leverages the study subjects initially assigned to control status as an unexposed reference population; we then employ a bespoke instrumental variable analysis, where the key assumption is “partial exchangeability” of the association between a covariate and an outcome in the treatment and control arms. We provide a formal description of the conditions for identification of causal effects, illustrate the method using simulations, and provide an empirical application.