Showing 1–17 of 17 results for author: Phillips, R

A Causal Inference Approach for Evaluating Diagnostic Tests and AI-Enabled Medical Devices: From Effect Modification to Information-Augmented Decision-Making

Authors: Wenxin Zhang, Rachael Phillips, Mark van der Laan

Abstract: Diagnostic medical tests and devices provide useful information for evaluating the potential benefits and risks of therapeutic treatments. However, unlike treatments, their impact on health outcomes is generally indirect because measuring diagnostic information typically does not itself affect patient outcomes, which complicates evaluation of their effectiveness. In this work, we develop a causal… ▽ More Diagnostic medical tests and devices provide useful information for evaluating the potential benefits and risks of therapeutic treatments. However, unlike treatments, their impact on health outcomes is generally indirect because measuring diagnostic information typically does not itself affect patient outcomes, which complicates evaluation of their effectiveness. In this work, we develop a causal inference approach for evaluating diagnostic tests by distinguishing explanatory and pragmatic effectiveness. Explanatory effectiveness evaluates whether a diagnostic test result provides treatment-relevant information beyond baseline covariates by explaining additional treatment-effect heterogeneity, which we characterize using a variance-based treatment-effect variable importance measure. Pragmatic effectiveness evaluates whether incorporating this information into personalized treatment decisions improves expected outcomes, a question central to decision-making for patients, clinicians, and other health care stakeholders. We formalize pragmatic effectiveness as a contrast between expected outcomes under optimal personalized treatment rules defined with and without access to the diagnostic test result. We establish identification of the proposed estimand and provide Targeted Maximum Likelihood Estimation (TMLE) and cross-validated TMLE procedures for nonparametric estimation and inference. Simulation studies and a synthetic colorectal cancer application illustrate the proposed estimands and estimation performance. More broadly, this approach provides a causal inference perspective for evaluating AI-enabled devices by distinguishing their dual roles as information-enrichment and personalized decision-optimization tools, clarifying whether AI improves outcomes by expanding information for downstream decisions, improving the decision rule used to act on that information, or through both pathways. △ Less

Submitted 19 August, 2026; originally announced August 2026.

Improving the Efficiency of Subgroup Analysis in Randomized Controlled Trials with TMLE

Authors: Sky Qiu, Nerissa Nance, Rachael Phillips, Jens Tarp, Maya Petersen, Mark van der Laan

Abstract: Subgroup analyses within randomized controlled trials are often underpowered due to limited sample sizes. We address this challenge by leveraging trial participants outside the subgroup of interest to augment estimation within the subgroup. Specifically, we study two Targeted Maximum Likelihood Estimators (TMLEs) that borrow information from non-subgroup participants within the same trial: a TMLE… ▽ More Subgroup analyses within randomized controlled trials are often underpowered due to limited sample sizes. We address this challenge by leveraging trial participants outside the subgroup of interest to augment estimation within the subgroup. Specifically, we study two Targeted Maximum Likelihood Estimators (TMLEs) that borrow information from non-subgroup participants within the same trial: a TMLE with pooled regression (TMLE-PR) and an Adaptive Targeted Maximum Likelihood Estimator (A-TMLE). Both estimators enable information sharing without relying on any external real-world data, thereby capitalizing on key strengths of the trial: most importantly, the protection against bias afforded by the randomized treatment, but also harmonized data collection, and consistent treatment and outcome definitions. The general strategy proposed here directly advances the priorities of key regulatory agencies, including the FDA, by improving the precision of subgroup-specific treatment effect estimates without introducing external sources of bias, thereby facilitating rigorous inference to support equitable labeling, access, and post-market evaluation. In a case study based on analysis of data from a cardiovascular outcome trial (LEADER, NCT01179048), we estimate the risk reduction of major adverse cardiac events (MACE) under liraglutide treatment among Black and Asian subgroups -- each comprising less than 10\% of the trial population -- using the proposed estimators that borrow information from the remainder of the trial. Using A-TMLE, in particular, we find estimated absolute MACE risk reductions of 1.6, 1.5, and 1.5 percentage points among Asian participants and 2.1, 2.0, and 2.1 percentage points among Black participants at 365, 540, and 730 days, respectively, with 95\% confidence intervals excluding the null at each time point. △ Less

Submitted 14 May, 2026; originally announced May 2026.

Hazard-Based Targeted Maximum Likelihood Estimation for Survival in Resampling Designs

Authors: Kirsten E. Landsiedel, Rachael V. Phillips, Maya L. Petersen, Mark J. van der Laan

Abstract: Survival is a key metric for evaluating standards of care for people living with HIV. In resource-limited settings, high rates of loss to follow-up (LTFU) often result in underestimation of mortality when only observed deaths are considered. Resampling, which tracks a subset of LTFU patients to ascertain their outcomes, mitigates bias and improves survival estimates. However, common estimators for… ▽ More Survival is a key metric for evaluating standards of care for people living with HIV. In resource-limited settings, high rates of loss to follow-up (LTFU) often result in underestimation of mortality when only observed deaths are considered. Resampling, which tracks a subset of LTFU patients to ascertain their outcomes, mitigates bias and improves survival estimates. However, common estimators for survival in resampling designs, such as weighted Kaplan-Meier (KM), fail to leverage covariate information collected during repeated clinic visits, even though this information is highly predictive of survival. We propose a Targeted Maximum Likelihood Estimator (TMLE) for survival in resampling designs, which addresses these limitations by leveraging baseline and longitudinal covariates to achieve greater efficiency. Our TMLE is a plug-in estimator and is robust to misspecification of the initial model for the conditional hazard of death, guaranteeing consistency of our estimator due to known resampling probabilities. We present: (1) a fully efficient TMLE for data from resampling studies with fixed follow-up time for all participants and (2) an inverse probability of censoring weighted (IPCW) TMLE that accounts for varied follow-up times by stratifying on patients with sufficient follow-up to evaluate survival. This IPCW-TMLE can be made highly efficient through nonparametric or targeted estimation of the follow-up censoring mechanism. In simulations, our TMLE reduced variance by up to 55% compared with the commonly used weighted KM estimator while preserving nominal confidence interval coverage. These findings demonstrate the potential of our TMLE to improve survival estimation in resampling designs, offering a robust and resource-efficient framework for HIV research. Keywords: Resampling designs, Survival analysis, Targeted Maximum Likelihood Estimation, Inverse probability weighting △ Less

Submitted 18 November, 2025; originally announced November 2025.

Comments: 28 pages, 5 figures

Performance of Cross-Validated Targeted Maximum Likelihood Estimation

Authors: Matthew J. Smith, Rachael V. Phillips, Camille Maringe, Miguel Angel Luque-Fernandez

Abstract: Background: Advanced methods for causal inference, such as targeted maximum likelihood estimation (TMLE), require certain conditions for statistical inference. However, in situations where there is not differentiability due to data sparsity or near-positivity violations, the Donsker class condition is violated. In such situations, TMLE variance can suffer from inflation of the type I error and poo… ▽ More Background: Advanced methods for causal inference, such as targeted maximum likelihood estimation (TMLE), require certain conditions for statistical inference. However, in situations where there is not differentiability due to data sparsity or near-positivity violations, the Donsker class condition is violated. In such situations, TMLE variance can suffer from inflation of the type I error and poor coverage, leading to conservative confidence intervals. Cross-validation of the TMLE algorithm (CVTMLE) has been suggested to improve on performance compared to TMLE in settings of positivity or Donsker class violations. We aim to investigate the performance of CVTMLE compared to TMLE in various settings. Methods: We utilised the data-generating mechanism as described in Leger et al. (2022) to run a Monte Carlo experiment under different Donsker class violations. Then, we evaluated the respective statistical performances of TMLE and CVTMLE with different super learner libraries, with and without regression tree methods. Results: We found that CVTMLE vastly improves confidence interval coverage without adversely affecting bias, particularly in settings with small sample sizes and near-positivity violations. Furthermore, incorporating regression trees using standard TMLE with ensemble super learner-based initial estimates increases bias and variance leading to invalid statistical inference. Conclusions: It has been shown that when using CVTMLE the Donsker class condition is no longer necessary to obtain valid statistical inference when using regression trees and under either data sparsity or near-positivity violations. We show through simulations that CVTMLE is much less sensitive to the choice of the super learner library and thereby provides better estimation and inference in cases where the super learner library uses more flexible candidates and is prone to overfitting. △ Less

Submitted 18 September, 2024; v1 submitted 17 September, 2024; originally announced September 2024.

Comments: 20 pages, 3 figures, 1 table

Variational inference of effective range parameters for ${}^3$He-${}^4$He scattering

Authors: Andrius Burnelis, Vojta Kejzlar, Daniel R. Phillips

Abstract: We use two different methods, Monte Carlo sampling and variational inference (VI), to perform a Bayesian calibration of the effective-range parameters in ${}^3$He-${}^4$He elastic scattering. The parameters are calibrated to data from a recent set of $^{3}$He-${}^4$He elastic scattering differential cross section measurements. Analysis of these data for $E_{\rm lab} \leq 4.3$ MeV yields a unimodal… ▽ More We use two different methods, Monte Carlo sampling and variational inference (VI), to perform a Bayesian calibration of the effective-range parameters in ${}^3$He-${}^4$He elastic scattering. The parameters are calibrated to data from a recent set of $^{3}$He-${}^4$He elastic scattering differential cross section measurements. Analysis of these data for $E_{\rm lab} \leq 4.3$ MeV yields a unimodal posterior for which both methods obtain the same structure. However, the effective-range expansion amplitude does not account for the $7/2^-$ state of ${}^7$Be so, even after calibration, the description of data at the upper end of this energy range is poor. The data up to $E_{\rm lab}=2.6$ MeV can be well described, but calibration to this lower-energy subset of the data yields a bimodal posterior. After adapting VI to treat such a multi-modal posterior we find good agreement between the VI results and those obtained with parallel-tempered Monte Carlo sampling. △ Less

Submitted 23 August, 2024; originally announced August 2024.

Comments: 13 Pages, 6 Figures

[Invited Discussion] Randomization Tests to Address Disruptions in Clinical Trials: A Report from the NISS Ingram Olkin Forum Series on Unplanned Clinical Trial Disruptions

Authors: Rachael V. Phillips, Mark J. van der Laan

Abstract: Disruptions in clinical trials may be due to external events like pandemics, warfare, and natural disasters. Resulting complications may lead to unforeseen intercurrent events (events that occur after treatment initiation and affect the interpretation of the clinical question of interest or the existence of the measurements associated with it). In Uschner et al. (2023), several example clinical tr… ▽ More Disruptions in clinical trials may be due to external events like pandemics, warfare, and natural disasters. Resulting complications may lead to unforeseen intercurrent events (events that occur after treatment initiation and affect the interpretation of the clinical question of interest or the existence of the measurements associated with it). In Uschner et al. (2023), several example clinical trial disruptions are described: treatment effect drift, population shift, change of care, change of data collection, and change of availability of study medication. A complex randomized controlled trial (RCT) setting with (planned or unplanned) intercurrent events is then described, and randomization tests are presented as a means for non-parametric inference that is robust to violations of assumption typically made in clinical trials. While estimation methods like Targeted Learning (TL) are valid in such settings, we do not see where the authors make the case that one should be going for a randomization test in such disrupted RCTs. In this discussion, we comment on the appropriateness of TL and the accompanying TL Roadmap in the context of disrupted clinical trials. We highlight a few key articles related to the broad applicability of TL for RCTs and real-world data (RWD) analyses with intercurrent events. We begin by introducing TL and motivating its utility in Section 2, and then in Section 3 we provide a brief overview of the TL Roadmap. In Section 4 we recite the example clinical trial disruptions presented in Uschner et al. (2023), discussing considerations and solutions based on the principles of TL. We request in an authors' rejoinder a clear theoretical demonstration with specific examples in this setting that a randomization test is the only valid inferential method relative to one based on following the TL Roadmap. △ Less

Submitted 16 August, 2024; originally announced August 2024.

Comments: This article is an un-refereed, Authors Original Version

Application of targeted maximum likelihood estimation in public health and epidemiological studies: a systematic review

Authors: Matthew J. Smith, Rachael V. Phillips, Miguel Angel Luque-Fernandez, Camille Maringe

Abstract: The Targeted Maximum Likelihood Estimation (TMLE) statistical data analysis framework integrates machine learning, statistical theory, and statistical inference to provide a least biased, efficient and robust strategy for estimation and inference of a variety of statistical and causal parameters. We describe and evaluate the epidemiological applications that have benefited from recent methodologic… ▽ More The Targeted Maximum Likelihood Estimation (TMLE) statistical data analysis framework integrates machine learning, statistical theory, and statistical inference to provide a least biased, efficient and robust strategy for estimation and inference of a variety of statistical and causal parameters. We describe and evaluate the epidemiological applications that have benefited from recent methodological developments. We conducted a systematic literature review in PubMed for articles that applied any form of TMLE in observational studies. We summarised the epidemiological discipline, geographical location, expertise of the authors, and TMLE methods over time. We used the Roadmap of Targeted Learning and Causal Inference to extract key methodological aspects of the publications. We showcase the contributions to the literature of these TMLE results. Of the 81 publications included, 25% originated from the University of California at Berkeley, where the framework was first developed by Professor Mark van der Laan. By the first half of 2022, 70% of the publications originated from outside the United States and explored up to 7 different epidemiological disciplines in 2021-22. Double-robustness, bias reduction and model misspecification were the main motivations that drew researchers towards the TMLE framework. Through time, a wide variety of methodological, tutorial and software-specific articles were cited, owing to the constant growth of methodological developments around TMLE. There is a clear dissemination trend of the TMLE framework to various epidemiological disciplines and to increasing numbers of geographical areas. The availability of R packages, publication of tutorial papers, and involvement of methodological experts in applied publications have contributed to an exponential increase in the number of studies that understood the benefits, and adoption, of TMLE. △ Less

Submitted 13 March, 2023; originally announced March 2023.

Comments: 42 pages, 2 figures, 2 tables

Multi-task Highly Adaptive Lasso

Authors: Ivana Malenica, Rachael V. Phillips, Daniel Lazzareschi, Jeremy R. Coyle, Romain Pirracchio, Mark J. van der Laan

Abstract: We propose a novel, fully nonparametric approach for the multi-task learning, the Multi-task Highly Adaptive Lasso (MT-HAL). MT-HAL simultaneously learns features, samples and task associations important for the common model, while imposing a shared sparse structure among similar tasks. Given multiple tasks, our approach automatically finds a sparse sharing structure. The proposed MTL algorithm at… ▽ More We propose a novel, fully nonparametric approach for the multi-task learning, the Multi-task Highly Adaptive Lasso (MT-HAL). MT-HAL simultaneously learns features, samples and task associations important for the common model, while imposing a shared sparse structure among similar tasks. Given multiple tasks, our approach automatically finds a sparse sharing structure. The proposed MTL algorithm attains a powerful dimension-free convergence rate of $o_p(n^{-1/4})$ or better. We show that MT-HAL outperforms sparsity-based MTL competitors across a wide range of simulation studies, including settings with nonlinear and linear relationships, varying levels of sparsity and task correlations, and different numbers of covariates and sample size. △ Less

Submitted 27 January, 2023; originally announced January 2023.

Evaluating and improving real-world evidence with Targeted Learning

Authors: Susan Gruber, Rachael V. Phillips, Hana Lee, John Concato, Mark van der Laan

Abstract: Purpose: The Targeted Learning roadmap provides a systematic guide for generating and evaluating real-world evidence (RWE). From a regulatory perspective, RWE arises from diverse sources such as randomized controlled trials that make use of real-world data, observational studies, and other study designs. This paper illustrates a principled approach to assessing the validity and interpretability of… ▽ More Purpose: The Targeted Learning roadmap provides a systematic guide for generating and evaluating real-world evidence (RWE). From a regulatory perspective, RWE arises from diverse sources such as randomized controlled trials that make use of real-world data, observational studies, and other study designs. This paper illustrates a principled approach to assessing the validity and interpretability of RWE. Methods: We applied the roadmap to a published observational study of the dose-response association between ritodrine hydrochloride and pulmonary edema among women pregnant with twins in Japan. The goal was to identify barriers to causal effect estimation beyond unmeasured confounding reported by the study's authors, and to explore potential options for overcoming the barriers that robustify results. Results: Following the roadmap raised issues that led us to formulate alternative causal questions that produced more reliable, interpretable RWE. The process revealed a lack of information in the available data to identify a causal dose-response curve. However, under explicit assumptions the effect of treatment with any amount of ritodrine versus none, albeit a less ambitious parameter, can be estimated from data. Conclusion: Before RWE can be used in support of clinical and regulatory decision-making, its quality and reliability must be systematically evaluated. The TL roadmap prescribes how to carry out a thorough, transparent, and realistic assessment of RWE. We recommend this approach be a routine part of any decision-making process. △ Less

Submitted 15 August, 2022; originally announced August 2022.

Comments: 13 pages, 4 figures

Targeted learning: Towards a future informed by real-world evidence

Authors: Susan Gruber, Rachael V. Phillips, Hana Lee, Martin Ho, John Concato, Mark J. van der Laan

Abstract: The 21st Century Cures Act of 2016 includes a provision for the U.S. Food and Drug Administration (FDA) to evaluate the potential use of real-world evidence (RWE) to support new indications for use for previously approved drugs, and to satisfy post-approval study requirements. Extracting reliable evidence from real-world data (RWD) is often complicated by a lack of treatment randomization, potenti… ▽ More The 21st Century Cures Act of 2016 includes a provision for the U.S. Food and Drug Administration (FDA) to evaluate the potential use of real-world evidence (RWE) to support new indications for use for previously approved drugs, and to satisfy post-approval study requirements. Extracting reliable evidence from real-world data (RWD) is often complicated by a lack of treatment randomization, potential intercurrent events, and informative loss to follow up. Targeted Learning (TL) is a sub-field of statistics that provides a rigorous framework to help address these challenges. The TL Roadmap offers a step-by-step guide to generating valid evidence and assessing its reliability. Following these steps produces an extensive amount of information for assessing whether the study provides reliable scientific evidence in support regulatory decision making. This paper presents two case studies that illustrate the utility of following the roadmap. We use targeted minimum loss-based estimation combined with super learning to estimate causal effects. We also compared these findings with those obtained from an unadjusted analysis, propensity score matching, and inverse probability weighting. Non-parametric sensitivity analyses illuminate how departures from (untestable) causal assumptions would affect point estimates and confidence interval bounds that would impact the substantive conclusion drawn from the study. TL's thorough approach to learning from data provides transparency, allowing trust in RWE to be earned whenever it is warranted. △ Less

Submitted 13 June, 2022; v1 submitted 17 May, 2022; originally announced May 2022.

Comments: 34 pages (25 pages main paper + references, 9 page Appendix), 6 figures version 2 corrected minor typos, numbering errors, etc

Practical considerations for specifying a super learner

Authors: Rachael V. Phillips, Mark J. van der Laan, Hana Lee, Susan Gruber

Abstract: Common tasks encountered in epidemiology, including disease incidence estimation and causal inference, rely on predictive modeling. Constructing a predictive model can be thought of as learning a prediction function, i.e., a function that takes as input covariate data and outputs a predicted value. Many strategies for learning these functions from data are available, from parametric regressions to… ▽ More Common tasks encountered in epidemiology, including disease incidence estimation and causal inference, rely on predictive modeling. Constructing a predictive model can be thought of as learning a prediction function, i.e., a function that takes as input covariate data and outputs a predicted value. Many strategies for learning these functions from data are available, from parametric regressions to machine learning algorithms. It can be challenging to choose an approach, as it is impossible to know in advance which one is the most suitable for a particular dataset and prediction task at hand. The super learner (SL) is an algorithm that alleviates concerns over selecting the one "right" strategy while providing the freedom to consider many of them, such as those recommended by collaborators, used in related research, or specified by subject-matter experts. It is an entirely pre-specified and data-adaptive strategy for predictive modeling. To ensure the SL is well-specified for learning the prediction function, the analyst does need to make a few important choices. In this Education Corner article, we provide step-by-step guidelines for making these choices, walking the reader through each of them and providing intuition along the way. In doing so, we aim to empower the analyst to tailor the SL specification to their prediction task, thereby ensuring their SL performs as well as possible. A flowchart provides a concise, easy-to-follow summary of key suggestions and heuristics, based on our accumulated experience, and guided by theory. △ Less

Submitted 14 March, 2023; v1 submitted 12 April, 2022; originally announced April 2022.

Comments: A revised version of this article, which incorporates several modifications based on referees' suggestions, has been published in the International Journal of Epidemiology by Oxford University Press

Journal ref: International Journal of Epidemiology, Volume 52, Issue 4, August 2023, Pages 1276-1285

Evaluating the Robustness of Targeted Maximum Likelihood Estimators via Realistic Simulations in Nutrition Intervention Trials

Authors: Haodong Li, Sonali Rosete, Jeremy Coyle, Rachael V. Phillips, Nima S. Hejazi, Ivana Malenica, Benjamin F. Arnold, Jade Benjamin-Chung, Andrew Mertens, John M. Colford Jr, Mark J. van der Laan, Alan E. Hubbard

Abstract: Several recently developed methods have the potential to harness machine learning in the pursuit of target quantities inspired by causal inference, including inverse weighting, doubly robust estimating equations and substitution estimators like targeted maximum likelihood estimation. There are even more recent augmentations of these procedures that can increase robustness, by adding a layer of cro… ▽ More Several recently developed methods have the potential to harness machine learning in the pursuit of target quantities inspired by causal inference, including inverse weighting, doubly robust estimating equations and substitution estimators like targeted maximum likelihood estimation. There are even more recent augmentations of these procedures that can increase robustness, by adding a layer of cross-validation (cross-validated targeted maximum likelihood estimation and double machine learning, as applied to substitution and estimating equation approaches, respectively). While these methods have been evaluated individually on simulated and experimental data sets, a comprehensive analysis of their performance across ``real-world'' simulations have yet to be conducted. In this work, we benchmark multiple widely used methods for estimation of the average treatment effect using ten different nutrition intervention studies data. A realistic set of simulations, based on a novel method, highly adaptive lasso, for estimating the data-generating distribution that guarantees a certain level of complexity (undersmoothing) is used to better mimic the complexity of the true data-generating distribution. We have applied this novel method for estimating the data-generating distribution by individual study and to subsequently use these fits to simulate data and estimate treatment effects parameters as well as their standard errors and resulting confidence intervals. Based on the analytic results, a general recommendation is put forth for use of the cross-validated variants of both substitution and estimating equation estimators. We conclude that the additional layer of cross-validation helps in avoiding unintentional over-fitting of nuisance parameter functionals and leads to more robust inferences. △ Less

Submitted 28 September, 2021; originally announced September 2021.

Personalized Online Machine Learning

Authors: Ivana Malenica, Rachael V. Phillips, Romain Pirracchio, Antoine Chambaz, Alan Hubbard, Mark J. van der Laan

Abstract: In this work, we introduce the Personalized Online Super Learner (POSL) -- an online ensembling algorithm for streaming data whose optimization procedure accommodates varying degrees of personalization. Namely, POSL optimizes predictions with respect to baseline covariates, so personalization can vary from completely individualized (i.e., optimization with respect to baseline covariate subject ID)… ▽ More In this work, we introduce the Personalized Online Super Learner (POSL) -- an online ensembling algorithm for streaming data whose optimization procedure accommodates varying degrees of personalization. Namely, POSL optimizes predictions with respect to baseline covariates, so personalization can vary from completely individualized (i.e., optimization with respect to baseline covariate subject ID) to many individuals (i.e., optimization with respect to common baseline covariates). As an online algorithm, POSL learns in real-time. POSL can leverage a diversity of candidate algorithms, including online algorithms with different training and update times, fixed algorithms that are never updated during the procedure, pooled algorithms that learn from many individuals' time-series, and individualized algorithms that learn from within a single time-series. POSL's ensembling of this hybrid of base learning strategies depends on the amount of data collected, the stationarity of the time-series, and the mutual characteristics of a group of time-series. In essence, POSL decides whether to learn across samples, through time, or both, based on the underlying (unknown) structure in the data. For a wide range of simulations that reflect realistic forecasting scenarios, and in a medical data application, we examine the performance of POSL relative to other current ensembling and online learning methods. We show that POSL is able to provide reliable predictions for time-series data and adjust to changing data-generating environments. We further cultivate POSL's practicality by extending it to settings where time-series enter/exit dynamically over chronological time. △ Less

Submitted 21 September, 2021; originally announced September 2021.

Does Bayesian Model Averaging improve polynomial extrapolations? Two toy problems as tests

Authors: M. A. Connell, I. Billig, D. R. Phillips

Abstract: We assess the accuracy of Bayesian polynomial extrapolations from small parameter values, x, to large values of x. We consider a set of polynomials of fixed order, intended as a proxy for a fixed-order effective field theory (EFT) description of data. We employ Bayesian Model Averaging (BMA) to combine results from different order polynomials (EFT orders). Our study considers two "toy problems" wh… ▽ More We assess the accuracy of Bayesian polynomial extrapolations from small parameter values, x, to large values of x. We consider a set of polynomials of fixed order, intended as a proxy for a fixed-order effective field theory (EFT) description of data. We employ Bayesian Model Averaging (BMA) to combine results from different order polynomials (EFT orders). Our study considers two "toy problems" where the underlying function used to generate data sets is known. We use Bayesian parameter estimation to extract the polynomial coefficients that describe these data at low x. A "naturalness" prior is imposed on the coefficients, so that they are O(1). We Bayesian-Model-Average different polynomial degrees by weighting each according to its Bayesian evidence and compare the predictive performance of this Bayesian Model Average with that of the individual polynomials. The credibility intervals on the BMA forecast have the stated coverage properties more consistently than does the highest evidence polynomial, though BMA does not necessarily outperform every polynomial. △ Less

Submitted 15 June, 2022; v1 submitted 10 June, 2021; originally announced June 2021.

Comments: 19 pages, 5 figures, v2 corresponds to published version

Journal ref: J. Phys. G 48 (2021) 10, 104001

Targeting Learning: Robust Statistics for Reproducible Research

Authors: Jeremy R. Coyle, Nima S. Hejazi, Ivana Malenica, Rachael V. Phillips, Benjamin F. Arnold, Andrew Mertens, Jade Benjamin-Chung, Weixin Cai, Sonali Dayal, John M. Colford Jr., Alan E. Hubbard, Mark J. van der Laan

Abstract: Targeted Learning is a subfield of statistics that unifies advances in causal inference, machine learning and statistical theory to help answer scientifically impactful questions with statistical confidence. Targeted Learning is driven by complex problems in data science and has been implemented in a diversity of real-world scenarios: observational studies with missing treatments and outcomes, per… ▽ More Targeted Learning is a subfield of statistics that unifies advances in causal inference, machine learning and statistical theory to help answer scientifically impactful questions with statistical confidence. Targeted Learning is driven by complex problems in data science and has been implemented in a diversity of real-world scenarios: observational studies with missing treatments and outcomes, personalized interventions, longitudinal settings with time-varying treatment regimes, survival analysis, adaptive randomized trials, mediation analysis, and networks of connected subjects. In contrast to the (mis)application of restrictive modeling strategies that dominate the current practice of statistics, Targeted Learning establishes a principled standard for statistical estimation and inference (i.e., confidence intervals and p-values). This multiply robust approach is accompanied by a guiding roadmap and a burgeoning software ecosystem, both of which provide guidance on the construction of estimators optimized to best answer the motivating question. The roadmap of Targeted Learning emphasizes tailoring statistical procedures so as to minimize their assumptions, carefully grounding them only in the scientific knowledge available. The end result is a framework that honestly reflects the uncertainty in both the background knowledge and the available data in order to draw reliable conclusions from statistical analyses - ultimately enhancing the reproducibility and rigor of scientific findings. △ Less

Submitted 12 June, 2020; originally announced June 2020.

Comments: 25 pages, 3 figures

MSC Class: 62A01 ACM Class: G.3

Disentangling Influence: Using Disentangled Representations to Audit Model Predictions

Authors: Charles T. Marx, Richard Lanas Phillips, Sorelle A. Friedler, Carlos Scheidegger, Suresh Venkatasubramanian

Abstract: Motivated by the need to audit complex and black box models, there has been extensive research on quantifying how data features influence model predictions. Feature influence can be direct (a direct influence on model outcomes) and indirect (model outcomes are influenced via proxy features). Feature influence can also be expressed in aggregate over the training or test data or locally with respect… ▽ More Motivated by the need to audit complex and black box models, there has been extensive research on quantifying how data features influence model predictions. Feature influence can be direct (a direct influence on model outcomes) and indirect (model outcomes are influenced via proxy features). Feature influence can also be expressed in aggregate over the training or test data or locally with respect to a single point. Current research has typically focused on one of each of these dimensions. In this paper, we develop disentangled influence audits, a procedure to audit the indirect influence of features. Specifically, we show that disentangled representations provide a mechanism to identify proxy features in the dataset, while allowing an explicit computation of feature influence on either individual outcomes or aggregate-level outcomes. We show through both theory and experiments that disentangled influence audits can both detect proxy features and show, for each individual or in aggregate, which of these proxy features affects the classifier being audited the most. In this respect, our method is more powerful than existing methods for ascertaining feature influence. △ Less

Submitted 20 June, 2019; originally announced June 2019.

Interpretable Active Learning

Authors: Richard L. Phillips, Kyu Hyun Chang, Sorelle A. Friedler

Abstract: Active learning has long been a topic of study in machine learning. However, as increasingly complex and opaque models have become standard practice, the process of active learning, too, has become more opaque. There has been little investigation into interpreting what specific trends and patterns an active learning strategy may be exploring. This work expands on the Local Interpretable Model-agno… ▽ More Active learning has long been a topic of study in machine learning. However, as increasingly complex and opaque models have become standard practice, the process of active learning, too, has become more opaque. There has been little investigation into interpreting what specific trends and patterns an active learning strategy may be exploring. This work expands on the Local Interpretable Model-agnostic Explanations framework (LIME) to provide explanations for active learning recommendations. We demonstrate how LIME can be used to generate locally faithful explanations for an active learning strategy, and how these explanations can be used to understand how different models and datasets explore a problem space over time. In order to quantify the per-subgroup differences in how an active learning strategy queries spatial regions, we introduce a notion of uncertainty bias (based on disparate impact) to measure the discrepancy in the confidence for a model's predictions between one subgroup and another. Using the uncertainty bias measure, we show that our query explanations accurately reflect the subgroup focus of the active learning queries, allowing for an interpretable explanation of what is being learned as points with similar sources of uncertainty have their uncertainty bias resolved. We demonstrate that this technique can be applied to track uncertainty bias over user-defined clusters or automatically generated clusters based on the source of uncertainty. △ Less

Submitted 23 June, 2018; v1 submitted 31 July, 2017; originally announced August 2017.

Comments: 13 pages, 8 figures, presented at 2018 Conference on Fairness, Accountability, and Transparency (FAT*), New York, New York, USA. Proceedings of the 1st Conference on Fairness, Accountability and Transparency, PMLR 81:49-61, 2018