Randomized experimentation (also known as A/B testing or bucket testing) is widely used in the internet industry to measure the metric impact obtained by different treatment variants. A/B tests identify the treatment variant showing the best performance, which then becomes the chosen or selected treatment for the entire population. However, the effect of a given treatment can differ across experimental units and a personalized approach for treatment selection can greatly improve upon the usual global selection strategy. In this work, we develop a framework for personalization through (i) estimation of heterogeneous treatment effect at either a cohort or member-level, followed by (ii) selection of optimal treatment variants for cohorts (or members) obtained through (deterministic or stochastic) constrained optimization.
We perform a two-fold evaluation of our proposed methods. First, a simulation analysis is conducted to study the effect of personalized treatment selection under carefully controlled settings. This simulation illustrates the differences between the proposed methods and the suitability of each with increasing uncertainty. We also demonstrate the effectiveness of the method through a real-life example related to serving notifications at Linkedin. The solution significantly outperformed both heuristic solutions and the global treatment selection baseline leading to a sizable win on top-line metrics like member visits.
The micro-randomized trial (MRT) is a sequential randomized experimental design to empirically evaluate the effectiveness of mobile health (mHealth) intervention components that may be delivered at hundreds or thousands of decision points. MRTs have motivated a new class of causal estimands, termed "causal excursion effects", for which semiparametric inference can be conducted via a weighted, centered least squares criterion (Boruvka et al., 2018). Existing methods assume between-subject independence and non-interference. Deviations from these assumptions often occur. In this paper, causal exc…
Background: Instrumental variables (IVs) can be used to provide evidence as to whether a treatment X has a causal effect on an outcome Y. Even if the instrument Z satisfies the three core IV assumptions of relevance, independence and the exclusion restriction, further assumptions are required to identify the average causal effect (ACE) of X on Y. Sufficient assumptions for this include: homogeneity in the causal effect of X on Y; homogeneity in the association of Z with X; and no effect modification (NEM). Methods: We describe the NO Simultaneous Heterogeneity (NOSH) assumption, which requires…
Southeast University（东南大学）；University of South Australia（南澳大学）
A central question in many fields of scientific research is to determine how an outcome would be affected by an action, or to measure the effect of an action (a.k.a treatment effect). In recent years, a need for estimating the heterogeneous treatment effects conditioning on the different characteristics of individuals has emerged from research fields such as personalized healthcare, social science, and online marketing. To meet the need, researchers and practitioners from different communities have developed algorithms by taking the treatment effect heterogeneity modeling approach and the upli…
The development of high-throughput sequencing and targeted therapies has led to the emergence of personalized medicine: a patient's molecular profile or the presence of a specific biomarker of drug response will correspond to a treatment recommendation made either by a physician or by a treatment assignment algorithm. The growing number of such algorithms raises the question of how to quantify their clinical impact knowing that a personalized medicine strategy will inherently include different versions of treatment. We thus specify an appropriate causal framework with multiple versions of trea…
Johns Hopkins University（约翰斯·霍普金斯大学）；Harvard T. H. Chan School of Public Health（哈佛陈曾熙公共卫生学院）
The goal of personalized decision making is to map a unit's characteristics to an action tailored to maximize the expected outcome for that unit. Obtaining high-quality mappings of this type is the goal of the dynamic regime literature. In healthcare settings, optimizing policies with respect to a particular causal pathway may be of interest as well. For example, we may wish to maximize the chemical effect of a drug given data from an observational study where the chemical effect of the drug on the outcome is entangled with the indirect effect mediated by differential adherence. In such cases,…
Mobile health studies can leverage longitudinal sensor data from smartphones to guide the application of personalized medical interventions. In this paper, we propose that adoption of an instrumental variable approach for randomized trials with imperfect compliance provides a natural framework for personalized causal inference of medication response in mobile health studies. Randomized treatment suggestions can be easily delivered to the study participants via electronic messages popping up on the smart-phone screen. Under quite general assumptions we can identify the causal effect of the actu…
We consider the problem of causal discovery (structure learning) from heterogeneous observational data. Most existing methods assume a homogeneous sampling scheme, which leads to misleading conclusions when violated in many applications. To this end, we propose a novel approach that exploits data heterogeneity to infer possibly cyclic causal structures from causally insufficient systems. The core idea is to model the direct causal effects as functions of exogenous covariates that properly explain data heterogeneity. We investigate structure identifiability properties of the proposed model. Str…
The participants in randomized trials and other studies used for causal inference are often not representative of the populations seen by clinical decision-makers. To account for differences between populations, researchers may consider standardizing results to a target population. We discuss several different types of homogeneity conditions that are relevant for standardization: Homogeneity of effect measures, homogeneity of counterfactual outcome state transition parameters, and homogeneity of counterfactual distributions. Each of these conditions can be used to show that a particular standa…
Recent work has made important contributions in the development of causally-interpretable meta-analysis. These methods transport treatment effects estimated in a collection of randomized trials to a target population of interest. Ideally, estimates targeted toward a specific population are more interpretable and relevant to policy-makers and clinicians. However, between-study heterogeneity not arising from differences in the distribution of treatment effect modifiers can raise difficulties in synthesizing estimates across trials. The existence of such heterogeneity, including variations in tre…
University of South Australia（南澳大学）；School of Computer and Information, Hefei University of Science and Technology（合肥理工大学计算机与信息学院）
In many applications, there is a need to predict the effect of an intervention on different individuals from data. For example, which customers are persuadable by a product promotion? which patients should be treated with a certain type of treatment? These are typical causal questions involving the effect or the change in outcomes made by an intervention. The questions cannot be answered with traditional classification methods as they only use associations to predict outcomes. For personalised marketing, these questions are often answered with uplift modelling. The objective of uplift modellin…
Hazard ratios are prone to selection bias, compromising their use as causal estimands. On the other hand, the hazard difference has been shown to remain unaffected by the selection of frailty factors over time. Therefore, observed hazard differences can be used as an unbiased estimator for the causal hazard differences in the absence of confounding. However, in the presence of effect (on the hazard) heterogeneity, the hazard difference is also affected by selection. In this work, we formalize how the observed hazard difference (from a randomized controlled trial) evolves by selecting favourabl…
Multi-task learning (MTL) is a novel framework to learn several tasks simultaneously with a single shared network where each task has its distinct personalized header network for fine-tuning. MTL can be implemented in federated learning settings as well, in which tasks are distributed across clients. In federated settings, the statistical heterogeneity due to different task complexities and data heterogeneity due to non-iid nature of local datasets can both degrade the learning performance of the system. In addition, tasks can negatively affect each other's learning performance due to negative…
Personalized Binomial DAGs Learning with Network Structured Covariates
Booth School of Business, University of Chicago（芝加哥大学布斯商学院）；University of Michigan（密歇根大学）；Ant Financial Group（蚂蚁集团）；Marshall School of Business, University of Southern California（南加州大学马歇尔商学院）
A Doubly Robust Machine Learning Approach for Disentangling Treatment Effect Heterogeneity with Functional Outcomes
Sant’Anna School of Advanced Studies（圣安娜高等研究学院）；School of Pharmaceutical Science, University of Geneva（日内瓦大学药学院）；Department of Statistics & Data Science, Carnegie Mellon University（卡内基梅隆大学统计与数据科学系）；Department of Statistics, Penn State University（宾夕法尼亚州立大学统计系）
Age-Dependent Heterogeneity in the Association Between Physical Activity and Mental Distress: A Causal Machine Learning Analysis of 3.2 Million U.S. Adults
Department of Statistical Science, Duke University（杜克大学统计科学系）
Patient-Specific Models of Treatment Effects Explain Heterogeneity in Tuberculosis
Pitt School of Medicine（匹兹堡大学医学院）；Carnegie Mellon University（卡内基梅隆大学）；University of Wisconsin, Madison（威斯康星大学麦迪逊分校）；MBZUAI（穆罕默德·本·扎耶德人工智能大学）；Petuum Inc.（Petuum公司）
We study the problem of learning conditional average treatment effects (CATE) from observational data with unobserved confounders. The CATE function maps baseline covariates to individual causal effect predictions and is key for personalized assessments. Recent work has focused on how to learn CATE under unconfoundedness, i.e., when there are no unobserved confounders. Since CATE may not be identified when unconfoundedness is violated, we develop a functional interval estimator that predicts bounds on the individual causal effects under realistic violations of unconfoundedness. Our estimator t…
It is known that the hazard ratio lacks a useful causal interpretation. Even for data from a randomized controlled trial, the hazard ratio suffers from built-in selection bias as, over time, the individuals at risk in the exposed and unexposed are no longer exchangeable. In this work, we formalize how the observed hazard ratio evolves and deviates from the causal hazard ratio of interest in the presence of heterogeneity of the hazard of unexposed individuals (frailty) and heterogeneity in effect (individual modification). For the case of effect heterogeneity, we define the causal hazard ratio.…
Oslo University Hospital（奥斯陆大学医院）；University of Oslo（奥斯陆大学）；Leiden University Medical Center（莱顿大学医学中心）；Leiden University（莱顿大学）；Erasmus Medical Center, University Medical Center Rotterdam（伊拉斯姆斯医学中心，鹿特丹大学医学中心）
Background: Mendelian randomization (MR) is a useful approach to causal inference from observational studies when randomised controlled trials are not feasible. However, study heterogeneity of two association studies required in MR is often overlooked. When dealing with large studies, recently developed Bayesian MR is limited by its computational expensiveness. Methods: We addressed study heterogeneity by proposing a random effect Bayesian MR model with multiple exposures and outcomes. For large studies, we adopted a subset posterior aggregation method to tackle the problem of computation. In …
