Michele Santacatterina
Research Subjects
Michele Santacatterina has a total of 41 co-authors. Here are the top co-authors by number of shared publications:
Nathan Kallus
School of Operations Research and Information Engineering and Cornell Tech, Cornell University , New York 10044 , New York , USA
2 shared publicationsAmina Ahmed
Atrium Health
1 shared publicationAnders Sönnerborg
Department of Medicine, Karolinska University Hospital, Stockholm, Sweden
1 shared publication- Andrea A. Berry
Center for Vaccine Development and Global Health, University of Maryland School of Medicine, Baltimore, USA
1 shared publication Anna Mia Ekström
Department of Public Health Sciences, Karolinska Institutet, Stockholm, Sweden
1 shared publicationAustin Lyles Seals
Wake Forest School of Medicine
1 shared publication
Latest Publications
- 13 February 2026
- Published by Oxford University Press (OUP) in Biometrika
- Vol. 113 (2)
Nonparametric efficient estimation of marginal structural models with continuous time-varying treatments
Summary: Marginal structural models are a popular method for estimating causal effects in the presence of time-varying exposures. In spite of their popularity, no scalable nonparametric estimator exists for marginal structural models with multi-valued or continuous time-varying treatments. In this paper, we combine flexible, data-adaptive regression methods, including ensemble learning techniques, with recent developments in semiparametric efficiency theory for longitudinal studies to propose such an estimator. The proposed estimator is based on a study of the nonparametric identifying functional, including first-order von Mises expansions, as well as the efficient influence function and the efficiency bound. We show conditions under which the proposed estimators are efficient, asymptotically normal and sequentially doubly robust. We perform a simulation study to illustrate the properties of the estimators, and present the results of our motivating study on a COVID-19 dataset, studying the impact of mobility on the cumulative number of observed cases.
- 13 February 2026
- Published by Oxford University Press (OUP) in Biometrika
- Vol. 113 (2)
Nonparametric efficient estimation of marginal structural models with continuous time-varying treatments
Summary: Marginal structural models are a popular method for estimating causal effects in the presence of time-varying exposures. In spite of their popularity, no scalable nonparametric estimator exists for marginal structural models with multi-valued or continuous time-varying treatments. In this paper, we combine flexible, data-adaptive regression methods, including ensemble learning techniques, with recent developments in semiparametric efficiency theory for longitudinal studies to propose such an estimator. The proposed estimator is based on a study of the nonparametric identifying functional, including first-order von Mises expansions, as well as the efficient influence function and the efficiency bound. We show conditions under which the proposed estimators are efficient, asymptotically normal and sequentially doubly robust. We perform a simulation study to illustrate the properties of the estimators, and present the results of our motivating study on a COVID-19 dataset, studying the impact of mobility on the cumulative number of observed cases.
- 15 March 2025
- Published by Wiley in Statistics in Medicine
- Vol. 44 (6) , e70017
Identification and Estimation of Causal Effects Using Non‐Concurrent Controls in Platform Trials
Platform trials are multi‐arm designs that simultaneously evaluate multiple treatments for a single disease within the same overall trial structure. Unlike traditional randomized controlled trials, they allow treatment arms to enter and exit the trial at distinct times while maintaining a control arm throughout. This control arm comprises both concurrent controls, where participants are randomized concurrently to either the treatment or control arm, and non‐concurrent controls, who enter the trial when the treatment arm under study is unavailable. While flexible, platform trials introduce the challenge of using non‐concurrent controls, raising questions about estimating treatment effects. Specifically, which estimands should be targeted? Under what assumptions can these estimands be identified and estimated? Are there any efficiency gains? In this article, we discuss issues related to the identification and estimation assumptions of common choices of estimand. We conclude that the most robust strategy to increase efficiency without imposing unwarranted assumptions is to target the concurrent average treatment effect (cATE), the ATE among only concurrent units, using a covariate‐adjusted doubly robust estimator. Our studies suggest that, for the purpose of obtaining efficiency gains, collecting important prognostic variables is more important than relying on non‐concurrent controls. We also discuss the perils of targeting ATE due to an untestable extrapolation assumption that will often be invalid. We provide simulations illustrating our points and an application to the ACTT platform trial, resulting in a 20% improvement in precision compared to the naive estimator that ignores non‐concurrent controls and prognostic variables.
- 15 March 2025
- Published by Wiley in Statistics in Medicine
- Vol. 44 (6) , e70017
Identification and Estimation of Causal Effects Using Non‐Concurrent Controls in Platform Trials
Platform trials are multi‐arm designs that simultaneously evaluate multiple treatments for a single disease within the same overall trial structure. Unlike traditional randomized controlled trials, they allow treatment arms to enter and exit the trial at distinct times while maintaining a control arm throughout. This control arm comprises both concurrent controls, where participants are randomized concurrently to either the treatment or control arm, and non‐concurrent controls, who enter the trial when the treatment arm under study is unavailable. While flexible, platform trials introduce the challenge of using non‐concurrent controls, raising questions about estimating treatment effects. Specifically, which estimands should be targeted? Under what assumptions can these estimands be identified and estimated? Are there any efficiency gains? In this article, we discuss issues related to the identification and estimation assumptions of common choices of estimand. We conclude that the most robust strategy to increase efficiency without imposing unwarranted assumptions is to target the concurrent average treatment effect (cATE), the ATE among only concurrent units, using a covariate‐adjusted doubly robust estimator. Our studies suggest that, for the purpose of obtaining efficiency gains, collecting important prognostic variables is more important than relying on non‐concurrent controls. We also discuss the perils of targeting ATE due to an untestable extrapolation assumption that will often be invalid. We provide simulations illustrating our points and an application to the ACTT platform trial, resulting in a 20% improvement in precision compared to the naive estimator that ignores non‐concurrent controls and prognostic variables.
- 12 January 2023
- Published by SAGE Publications in Statistical Methods in Medical Research
- Vol. 32 (3) , 524-538
Robust weights that optimally balance confounders for estimating marginal hazard ratios
Covariate balance is crucial in obtaining unbiased estimates of treatment effects in observational studies. Methods that target covariate balance have been successfully proposed and largely applied to estimate treatment effects on continuous outcomes. However, in many medical and epidemiological applications, the interest lies in estimating treatment effects on time-to-event outcomes. With this type of data, one of the most common estimands of interest is the marginal hazard ratio of the Cox proportional hazards model. In this article, we start by presenting robust orthogonality weights, a set of weights obtained by solving a quadratic constrained optimization problem that maximizes precision while constraining covariate balance defined as the correlation between confounders and treatment. By doing so, robust orthogonality weights optimally deal with both binary and continuous treatments. We then evaluate the performance of the proposed weights in estimating marginal hazard ratios of binary and continuous treatments with time-to-event outcomes in a simulation study. We finally apply robust orthogonality weights in the evaluation of the effect of hormone therapy on time to coronary heart disease and on the effect of red meat consumption on time to colon cancer among 24,069 postmenopausal women enrolled in the Women’s Health Initiative observational study.
- 12 January 2023
- Published by SAGE Publications in Statistical Methods in Medical Research
- Vol. 32 (3) , 524-538
Robust weights that optimally balance confounders for estimating marginal hazard ratios
Covariate balance is crucial in obtaining unbiased estimates of treatment effects in observational studies. Methods that target covariate balance have been successfully proposed and largely applied to estimate treatment effects on continuous outcomes. However, in many medical and epidemiological applications, the interest lies in estimating treatment effects on time-to-event outcomes. With this type of data, one of the most common estimands of interest is the marginal hazard ratio of the Cox proportional hazards model. In this article, we start by presenting robust orthogonality weights, a set of weights obtained by solving a quadratic constrained optimization problem that maximizes precision while constraining covariate balance defined as the correlation between confounders and treatment. By doing so, robust orthogonality weights optimally deal with both binary and continuous treatments. We then evaluate the performance of the proposed weights in estimating marginal hazard ratios of binary and continuous treatments with time-to-event outcomes in a simulation study. We finally apply robust orthogonality weights in the evaluation of the effect of hormone therapy on time to coronary heart disease and on the effect of red meat consumption on time to colon cancer among 24,069 postmenopausal women enrolled in the Women’s Health Initiative observational study.
- Open Access
- 1 January 2022
- Published by Walter de Gruyter GmbH in Journal of Causal Inference
- Vol. 10 (1) , 123-140
Optimal weighting for estimating generalized average treatment effects
In causal inference, a variety of causal effect estimands have been studied, including the sample, uncensored, target, conditional, optimal subpopulation, and optimal weighted average treatment effects. Ad hoc methods have been developed for each estimand based on inverse probability weighting (IPW) and on outcome regression modeling, but these may be sensitive to model misspecification, practical violations of positivity, or both. The contribution of this article is twofold. First, we formulate the generalized average treatment effect (GATE) to unify these causal estimands as well as their IPW estimates. Second, we develop a method based on Kernel optimal matching (KOM) to optimally estimate GATE and to find the GATE most easily estimable by KOM, which we term the Kernel optimal weighted average treatment effect. KOM provides uniform control on the conditional mean squared error of a weighted estimator over a class of models while simultaneously controlling for precision. We study its theoretical properties and evaluate its comparative performance in a simulation study. We illustrate the use of KOM for GATE estimation in two case studies: comparing spine surgical interventions and studying the effect of peer support on people living with HIV.
- 1 January 2022
- Published by Walter de Gruyter GmbH in Journal of Causal Inference
- Vol. 10 (1) , 123-140
Open AccessOptimal weighting for estimating generalized average treatment effects
In causal inference, a variety of causal effect estimands have been studied, including the sample, uncensored, target, conditional, optimal subpopulation, and optimal weighted average treatment effects. Ad hoc methods have been developed for each estimand based on inverse probability weighting (IPW) and on outcome regression modeling, but these may be sensitive to model misspecification, practical violations of positivity, or both. The contribution of this article is twofold. First, we formulate the generalized average treatment effect (GATE) to unify these causal estimands as well as their IPW estimates. Second, we develop a method based on Kernel optimal matching (KOM) to optimally estimate GATE and to find the GATE most easily estimable by KOM, which we term the Kernel optimal weighted average treatment effect. KOM provides uniform control on the conditional mean squared error of a weighted estimator over a class of models while simultaneously controlling for precision. We study its theoretical properties and evaluate its comparative performance in a simulation study. We illustrate the use of KOM for GATE estimation in two case studies: comparing spine surgical interventions and studying the effect of peer support on people living with HIV.
- 4 November 2021
- Published by Massachusetts Medical Society in New England Journal of Medicine
- Vol. 385 (19) , 1817-1821
Prevention of Covid-19 with the BNT162b2 and mRNA-1273 Vaccines
Thompson et al. (July 22 issue)1 report on the effectiveness of messenger RNA (mRNA) vaccines against SARS-CoV-2 among U.S. health care workers, and their findings are consistent with those of other observational studies and randomized trials.2-4 Additional community-based studies are needed to further document vaccine effectiveness, especially in regions with low vaccination rates.
- 4 November 2021
- Published by Massachusetts Medical Society in New England Journal of Medicine
- Vol. 385 (19) , 1817-1821
Prevention of Covid-19 with the BNT162b2 and mRNA-1273 Vaccines
Thompson et al. (July 22 issue)1 report on the effectiveness of messenger RNA (mRNA) vaccines against SARS-CoV-2 among U.S. health care workers, and their findings are consistent with those of other observational studies and randomized trials.2-4 Additional community-based studies are needed to further document vaccine effectiveness, especially in regions with low vaccination rates.
- Open Access
Breakthrough SARS-CoV-2 Infections after Vaccination in North Carolina
Importance Real-world data are needed to assess incidence and factors associated with breakthrough SARS-CoV-2 infections following vaccination. Objective Estimate incidence of breakthrough infections and assess associations with risk factors using self-reported data from a large NC population sample. Design Prospective observational cohort study utilizing daily online survey data to capture information about COVID-19 symptoms, testing, and vaccination status. Setting Six health care systems in North Carolina with data collected between January 15, 2021 and September 24, 2021. Participants Adult study participants who reported full vaccination with a COVID-19 mRNA or J&J non-replicating viral vector vaccine (n =16,020). Exposures Potential community exposure to SARS-CoV-2. Main Outcome and Measures Self-reported breakthrough infection. Results SARS-CoV-2 infection after vaccination was self-reported in 1.9% of participants, with an incidence rate of 7.3 per 100,000 person-years. Younger age (45-64 vs. 18-44: HR (95% CI) = 0.65 (0.51 - 0.82); 65+ vs. 18-44: HR (95% CI) = 0.59 (0.39 - 0.90)), and vaccination with J&J Ad26.COV2.S were associated with a higher risk of breakthrough infection compared to vaccination with Pfizer BNT162b2 (Ad26.COV2.S vs. BNT162b2: HR (95% CI) = 2.23 (1.40 - 3.56)), while participants vaccinated with mRNA-1273 (mRNA-1273 vs. BNT162b2: HR (95% CI) = 0.69 (0.50 – 0.96) and those residing in urban counties experienced a lower rate of SARS-CoV-2 breakthrough infection compared with those from suburban (HR (95% CI) = 1.39 (1.01 – 1.90) or rural (HR (95% CI) = 1.57 (1.16 – 2.11) counties. There was no significant association between breakthrough infection and participant sex, race, healthcare worker status, prior COVID-19 infection, routine mask use, or overall vaccination rate in the county of residence. Conclusions and Relevance This NC community-based observational study showed that the proportion of the cohort who self-report breakthrough SARS-CoV-2 infections was 7.3 events per 100,000 person-years. Younger adults, those vaccinated with J&J Ad26.COV2.S, and those residing in suburban or rural counties were at higher risk of breakthrough infections and should be targeted for additional risk mitigation strategies to decrease community transmission. Trial Registration The COVID-19 Community Research Partnership is listed in clinicaltrials.gov (NCT04342884). Question What are the characteristics of those with breakthrough infections after SARS-CoV-2 vaccination in North Carolinaã Findings In this NC-based observational study of 16,020 participants, 1.9% self-reported a positive SARS-CoV-2 viral test at least 2 weeks following full vaccination, reflecting an event rate of 7.3 infections per 100,000 person years. Rates were higher among younger participants, participants from more rural areas in North Carolina, and those vaccinated with J&J Ad26.COV2.S. Meaning Our results show a relatively low rate of COVID-19 infection following full vaccination. Younger adults and those vaccinated with J&J Ad26.COV2.S should be targeted for additional risk mitigation strategies.
Open AccessBreakthrough SARS-CoV-2 Infections after Vaccination in North Carolina
Importance Real-world data are needed to assess incidence and factors associated with breakthrough SARS-CoV-2 infections following vaccination. Objective Estimate incidence of breakthrough infections and assess associations with risk factors using self-reported data from a large NC population sample. Design Prospective observational cohort study utilizing daily online survey data to capture information about COVID-19 symptoms, testing, and vaccination status. Setting Six health care systems in North Carolina with data collected between January 15, 2021 and September 24, 2021. Participants Adult study participants who reported full vaccination with a COVID-19 mRNA or J&J non-replicating viral vector vaccine (n =16,020). Exposures Potential community exposure to SARS-CoV-2. Main Outcome and Measures Self-reported breakthrough infection. Results SARS-CoV-2 infection after vaccination was self-reported in 1.9% of participants, with an incidence rate of 7.3 per 100,000 person-years. Younger age (45-64 vs. 18-44: HR (95% CI) = 0.65 (0.51 - 0.82); 65+ vs. 18-44: HR (95% CI) = 0.59 (0.39 - 0.90)), and vaccination with J&J Ad26.COV2.S were associated with a higher risk of breakthrough infection compared to vaccination with Pfizer BNT162b2 (Ad26.COV2.S vs. BNT162b2: HR (95% CI) = 2.23 (1.40 - 3.56)), while participants vaccinated with mRNA-1273 (mRNA-1273 vs. BNT162b2: HR (95% CI) = 0.69 (0.50 – 0.96) and those residing in urban counties experienced a lower rate of SARS-CoV-2 breakthrough infection compared with those from suburban (HR (95% CI) = 1.39 (1.01 – 1.90) or rural (HR (95% CI) = 1.57 (1.16 – 2.11) counties. There was no significant association between breakthrough infection and participant sex, race, healthcare worker status, prior COVID-19 infection, routine mask use, or overall vaccination rate in the county of residence. Conclusions and Relevance This NC community-based observational study showed that the proportion of the cohort who self-report breakthrough SARS-CoV-2 infections was 7.3 events per 100,000 person-years. Younger adults, those vaccinated with J&J Ad26.COV2.S, and those residing in suburban or rural counties were at higher risk of breakthrough infections and should be targeted for additional risk mitigation strategies to decrease community transmission. Trial Registration The COVID-19 Community Research Partnership is listed in clinicaltrials.gov (NCT04342884). Question What are the characteristics of those with breakthrough infections after SARS-CoV-2 vaccination in North Carolinaã Findings In this NC-based observational study of 16,020 participants, 1.9% self-reported a positive SARS-CoV-2 viral test at least 2 weeks following full vaccination, reflecting an event rate of 7.3 infections per 100,000 person years. Rates were higher among younger participants, participants from more rural areas in North Carolina, and those vaccinated with J&J Ad26.COV2.S. Meaning Our results show a relatively low rate of COVID-19 infection following full vaccination. Younger adults and those vaccinated with J&J Ad26.COV2.S should be targeted for additional risk mitigation strategies.
- 4 March 2021
- Published by Wiley in Statistics in Medicine
- Vol. 40 (10) , 2305-2320
More robust estimation of average treatment effects using kernel optimal matching in an observational study of spine surgical interventions
Inverse probability of treatment weighting (IPTW), which has been used to estimate average treatment effects (ATE) using observational data, tenuously relies on the positivity assumption and the correct specification of the treatment assignment model, both of which are problematic assumptions in many observational studies. Various methods have been proposed to overcome these challenges, including truncation, covariate‐balancing propensity scores, and stable balancing weights. Motivated by an observational study in spine surgery, in which positivity is violated and the true treatment assignment model is unknown, we present the use of optimal balancing by kernel optimal matching (KOM) to estimate ATE. By uniformly controlling the conditional mean squared error of a weighted estimator over a class of models, KOM simultaneously mitigates issues of possible misspecification of the treatment assignment model and is able to handle practical violations of the positivity assumption, as shown in our simulation study. Using data from a clinical registry, we apply KOM to compare two spine surgical interventions and demonstrate how the result matches the conclusions of clinical trials that IPTW estimates spuriously refute.
- 4 March 2021
- Published by Wiley in Statistics in Medicine
- Vol. 40 (10) , 2305-2320
More robust estimation of average treatment effects using kernel optimal matching in an observational study of spine surgical interventions
Inverse probability of treatment weighting (IPTW), which has been used to estimate average treatment effects (ATE) using observational data, tenuously relies on the positivity assumption and the correct specification of the treatment assignment model, both of which are problematic assumptions in many observational studies. Various methods have been proposed to overcome these challenges, including truncation, covariate‐balancing propensity scores, and stable balancing weights. Motivated by an observational study in spine surgery, in which positivity is violated and the true treatment assignment model is unknown, we present the use of optimal balancing by kernel optimal matching (KOM) to estimate ATE. By uniformly controlling the conditional mean squared error of a weighted estimator over a class of models, KOM simultaneously mitigates issues of possible misspecification of the treatment assignment model and is able to handle practical violations of the positivity assumption, as shown in our simulation study. Using data from a clinical registry, we apply KOM to compare two spine surgical interventions and demonstrate how the result matches the conclusions of clinical trials that IPTW estimates spuriously refute.
- Open Access
CAB: Continuous Adaptive Blending Estimator for Policy Evaluation and Learning
The ability to perform offline A/B-testing and off-policy learning using logged contextual bandit feedback is highly desirable in a broad range of applications, including recommender systems, search engines, ad placement, and personalized health care. Both offline A/B-testing and off-policy learning require a counterfactual estimator that evaluates how some new policy would have performed, if it had been used instead of the logging policy. In this paper, we identify a family of counterfactual estimators which subsumes most such estimators proposed to date. Our analysis of this family identifies a new estimator - called Continuous Adaptive Blending (CAB) - which enjoys many advantageous theoretical and practical properties. In particular, it can be substantially less biased than clipped Inverse Propensity Score (IPS) weighting and the Direct Method, and it can have less variance than Doubly Robust and IPS estimators. In addition, it is sub-differentiable such that it can be used for learning, unlike the SWITCH estimator. Experimental results show that CAB provides excellent evaluation accuracy and outperforms other counterfactual estimators in terms of learning performance.
Open AccessCAB: Continuous Adaptive Blending Estimator for Policy Evaluation and Learning
The ability to perform offline A/B-testing and off-policy learning using logged contextual bandit feedback is highly desirable in a broad range of applications, including recommender systems, search engines, ad placement, and personalized health care. Both offline A/B-testing and off-policy learning require a counterfactual estimator that evaluates how some new policy would have performed, if it had been used instead of the logging policy. In this paper, we identify a family of counterfactual estimators which subsumes most such estimators proposed to date. Our analysis of this family identifies a new estimator - called Continuous Adaptive Blending (CAB) - which enjoys many advantageous theoretical and practical properties. In particular, it can be substantially less biased than clipped Inverse Propensity Score (IPS) weighting and the Direct Method, and it can have less variance than Doubly Robust and IPS estimators. In addition, it is sub-differentiable such that it can be used for learning, unlike the SWITCH estimator. Experimental results show that CAB provides excellent evaluation accuracy and outperforms other counterfactual estimators in terms of learning performance.
- 27 December 2018
- Published by Wiley in Statistics in Medicine
- Vol. 38 (10) , 1891-1902
Optimal probability weights for estimating causal effects of time‐varying treatments with marginal structural Cox models
Marginal structural Cox models have been used to estimate the causal effect of a time‐varying treatment on a survival outcome in the presence of time‐dependent confounders. These methods rely on the positivity assumption, which states that the propensity scores are bounded away from zero and one. Practical violations of this assumption are common in longitudinal studies, resulting in extreme weights that may yield erroneous inferences. Truncation, which consists of replacing outlying weights with less extreme ones, is the most common approach to control for extreme weights to date. While truncation reduces the variability in the weights and the consequent sampling variability of the estimator, it can also introduce bias. Instead of truncated weights, we propose using optimal probability weights, defined as those that have a specified variance and the smallest Euclidean distance from the original, untruncated weights. The set of optimal weights is obtained by solving a constrained quadratic optimization problem. The proposed weights are evaluated in a simulation study and applied to the assessment of the effect of treatment on time to death among people in Sweden who live with human immunodeficiency virus and inject drugs.
- 27 December 2018
- Published by Wiley in Statistics in Medicine
- Vol. 38 (10) , 1891-1902
Optimal probability weights for estimating causal effects of time‐varying treatments with marginal structural Cox models
Marginal structural Cox models have been used to estimate the causal effect of a time‐varying treatment on a survival outcome in the presence of time‐dependent confounders. These methods rely on the positivity assumption, which states that the propensity scores are bounded away from zero and one. Practical violations of this assumption are common in longitudinal studies, resulting in extreme weights that may yield erroneous inferences. Truncation, which consists of replacing outlying weights with less extreme ones, is the most common approach to control for extreme weights to date. While truncation reduces the variability in the weights and the consequent sampling variability of the estimator, it can also introduce bias. Instead of truncated weights, we propose using optimal probability weights, defined as those that have a specified variance and the smallest Euclidean distance from the original, untruncated weights. The set of optimal weights is obtained by solving a constrained quadratic optimization problem. The proposed weights are evaluated in a simulation study and applied to the assessment of the effect of treatment on time to death among people in Sweden who live with human immunodeficiency virus and inject drugs.