Search

Existing methods that use propensity scores for heterogeneous treatment effect estimation on non-experimental data do not readily extend to the case of more than two treatment options. In this work, we develop a new propensity score-based method for heterogeneous treatment effect estimation when there are three or more treatment options, and prove that it generates unbiased estimates. We demonstrate our method on a real patient registry of patients in Singapore with diabetic dyslipidemia. On this dataset, our method generates heterogeneous treatment recommendations for patients among three options: Statins, fibrates, and non-pharmacological treatment to control patients' lipid ratios (total cholesterol divided by high-density lipoprotein level). In our numerical study, our proposed method generated more stable estimates compared to a benchmark method based on a multi-dimensional propensity score. [ABSTRACT FROM AUTHOR]

Copyright of Canadian Journal of Statistics is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

We describe a new method to combine propensity‐score matching with regression adjustment in treatment‐control studies when outcomes are binary by multiply imputing potential outcomes under control for the matched treated subjects. This enables the estimation of clinically meaningful measures of effect such as the risk difference. We used Monte Carlo simulation to explore the effect of the number of imputed potential outcomes under control for the matched treated subjects on inferences about the risk difference. We found that imputing potential outcomes under control (either single imputation or multiple imputation) resulted in a substantial reduction in bias compared with what was achieved using conventional nearest neighbor matching alone. Increasing the number of imputed potential outcomes under control resulted in more efficient estimation, with more efficient estimation of the estimated risk difference when increasing the number of the imputed potential outcomes. The greatest relative increase in efficiency was achieved by imputing five potential outcomes; once 20 outcomes under control were imputed for each matched treated subject, further improvements in efficiency were negligible. We also examined the effect of the number of these imputed potential outcomes on: (i) estimated standard errors; (ii) mean squared error; (iii) coverage of estimated confidence intervals. We illustrate the application of the method by estimating the effect on the risk of death within 1 year of prescribing beta‐blockers to patients discharged from hospital with a diagnosis of heart failure. [ABSTRACT FROM AUTHOR]

Blocking is commonly used in randomized experiments to increase efficiency of estimation. A generalization of blocking removes allocations with imbalance in covariate distributions between treated and control units, and then randomizes within the remaining set of allocations with balance. This idea of rerandomization was formalized by Morgan and Rubin (Annals of Statistics, 2012, 40, 1263–1282), who suggested using Mahalanobis distance between treated and control covariate means as the criterion for removing unbalanced allocations. Kallus (Journal of the Royal Statistical Society, Series B: Statistical Methodology, 2018, 80, 85–112) proposed reducing the set of balanced allocations to the minimum. Here we discuss the implication of such an 'optimal' rerandomization design for inferences to the units in the sample and to the population from which the units in the sample were randomly drawn. We argue that, in general, it is a bad idea to seek the optimal design for an inference because that inference typically only reflects uncertainty from the random sampling of units, which is usually hypothetical, and not the randomization of units to treatment versus control. [ABSTRACT FROM AUTHOR]

The weaponization of digital communications and social media to conduct disinformation campaigns at immense scale, speed, and reach presents new challenges to identify and counter hostile influence operations (IOs). This paper presents an end-to-end framework to automate detection of disinformation narratives, networks, and influential actors. The framework integrates natural language processing, machine learning, graph analytics, and a network causal inference approach to quantify the impact of individual actors in spreading IO narratives. We demonstrate its capability on real-world hostile IO campaigns with Twitter datasets collected during the 2017 French presidential elections and known IO accounts disclosed by Twitter over a broad range of IO campaigns (May 2007 to February 2020), over 50,000 accounts, 17 countries, and different account types including both trolls and bots. Our system detects IO accounts with 96% precision, 79% recall, and 96% area-under-the precision-recall (P-R) curve; maps out salient network communities; and discovers high-impact accounts that escape the lens of traditional impact statistics based on activity counts and network centrality. Results are corroborated with independent sources of known IO accounts from US Congressional reports, investigative journalism, and IO datasets provided by Twitter. [ABSTRACT FROM AUTHOR]

Data analyses typically rely upon assumptions about the missingness mechanisms that lead to observed versus missing data, assumptions that are typically unassessable. We explore an approach where the joint distribution of observed data and missing data are specified in a nonstandard way. In this formulation, which traces back to a representation of the joint distribution of the data and missingness mechanism, apparently first proposed by J. W. Tukey, the modeling assumptions about the distributions are either assessable or are designed to allow relatively easy incorporation of substantive knowledge about the problem at hand, thereby offering a possibly realistic portrayal of the data, both observed and missing. We develop Tukey’s representation for exponential-family models, propose a computationally tractable approach to inference in this class of models, and offer some general theoretical comments. We then illustrate the utility of this approach with an example in systems biology. [ABSTRACT FROM AUTHOR]

A catalytic prior distribution is designed to stabilize a high-dimensional “working model” by shrinking it toward a “simplified model.” The shrinkage is achieved by supplementing the observed data with a small amount of “synthetic data” generated from a predictive distribution under the simpler model. We apply this framework to generalized linear models, where we propose various strategies for the specification of a tuning parameter governing the degree of shrinkage and study resultant theoretical properties. In simulations, the resulting posterior estimation using such a catalytic prior outperforms maximum likelihood estimation from the working model and is generally comparable with or superior to existing competitive methods in terms of frequentist prediction accuracy of point estimation and coverage accuracy of interval estimation. The catalytic priors have simple interpretations and are easy to formulate. [ABSTRACT FROM AUTHOR]

Matching on an estimated propensity score is frequently used to estimate the effects of treatments from observational data. Since the 1970s, different authors have proposed methods to combine matching at the design stage with regression adjustment at the analysis stage when estimating treatment effects for continuous outcomes. Previous work has consistently shown that the combination has generally superior statistical properties than either method by itself. In biomedical and epidemiological research, survival or time-to-event outcomes are common. We propose a method to combine regression adjustment and propensity score matching to estimate survival curves and hazard ratios based on estimating an imputed potential outcome under control for each successfully matched treated subject, which is accomplished using either an accelerated failure time parametric survival model or a Cox proportional hazard model that is fit to the matched control subjects. That is, a fitted model is then applied to the matched treated subjects to allow simulation of the missing potential outcome under control for each treated subject. Conventional survival analyses (e.g., estimation of survival curves and hazard ratios) can then be conducted using the observed outcome under treatment and the imputed outcome under control. We evaluated the repeated-sampling bias of the proposed methods using simulations. When using nearest neighbor matching, the proposed method resulted in decreased bias compared to crude analyses in the matched sample. We illustrate the method in an example prescribing beta-blockers at hospital discharge to patients hospitalized with heart failure. [ABSTRACT FROM AUTHOR]

Models for analysing multivariate datasets with missing values require strong, often unassessable, assumptions. The most common of these is that the mechanism that created the missing data is ignorable, which is a two-fold assumption dependent on the mode of inference. The first part, which is the focus here, under the Bayesian and direct-likelihood paradigms requires that the missing data be missing at random; in contrast, the frequentist-likelihood paradigm demands that the missing data mechanism always produce missing at random data, a condition known as missing always at random. Under certain regularity conditions, assuming missing always at random leads to a condition that can be tested using the observed data alone, namely that the missing data indicators depend only on fully observed variables. In this note we propose three different diagnostic tests that not only indicate when this assumption is incorrect but also suggest which variables are the most likely culprits. Although missing always at random is not a necessary condition to ensure validity under the Bayesian and direct-likelihood paradigms, it is sufficient, and evidence of its violation should encourage the careful statistician to conduct targeted sensitivity analyses. [ABSTRACT FROM AUTHOR]

Consider a statistical analysis that draws causal inferences from an observational dataset, inferences that are presented as being valid in the standard frequentist senses; i.e. the analysis produces: (1) consistent point estimates, (2) valid p-values, valid in the sense of rejecting true null hypotheses at the nominal level or less often, and/or (3) confidence intervals, which are presented as having at least their nominal coverage for their estimands. For the hypothetical validity of these statements, the analysis must embed the observational study in a hypothetical randomized experiment that created the observed data, or a subset of that hypothetical randomized data set. This multistage effort with thought-provoking tasks involves: (1) a purely conceptual stage that precisely formulate the causal question in terms of a hypothetical randomized experiment where the exposure is assigned to units; (2) a design stage that approximates a randomized experiment before any outcome data are observed, (3) a statistical analysis stage comparing the outcomes of interest in the exposed and non-exposed units of the hypothetical randomized experiment, and (4) a summary stage providing conclusions about statistical evidence for the sizes of possible causal effects. Stages 2 and 3 may rely on modern computing to implement the effort, whereas Stage 1 demands careful scientific argumentation to make the embedding plausible to scientific readers of the proffered statistical analysis. Otherwise, the resulting analysis is vulnerable to criticism for being simply a presentation of scientifically meaningless arithmetic calculations. The conceptually most demanding tasks are often the most scientifically interesting to the dedicated researcher and readers of the resulting statistical analyses. This perspective is rarely implemented with any rigor, for example, completely eschewing the first stage. We illustrate our approach using an example examining the effect of parental smoking on children's lung function collected in families living in East Boston in the 1970s. [ABSTRACT FROM AUTHOR]

Although complete randomization ensures covariate balance on average, the chance of observing significant differences between treatment and control covariate distributions increases with many covariates. Rerandomization discards randomizations that do not satisfy a predetermined covariate balance criterion, generally resulting in better covariate balance and more precise estimates of causal effects. Previous theory has derived finite sample theory for rerandomization under the assumptions of equal treatment group sizes, Gaussian covariate and outcome distributions, or additive causal effects, but not for the general sampling distribution of the difference-in-means estimator for the average causal effect. We develop asymptotic theory for rerandomization without these assumptions, which reveals a non-Gaussian asymptotic distribution for this estimator, specifically a linear combination of a Gaussian random variable and truncated Gaussian random variables. This distribution follows because rerandomization affects only the projection of potential outcomes onto the covariate space but does not affect the corresponding orthogonal residuals. We demonstrate that, compared with complete randomization, rerandomization reduces the asymptotic quantile ranges of the difference-in-means estimator. Moreover, our work constructs accurate large-sample confidence intervals for the average causal effect. [ABSTRACT FROM AUTHOR]

The seminal work of Morgan & Rubin (2012) considers rerandomization for all the units at one time.In practice, however, experimenters may have to rerandomize units sequentially. For example, a clinician studying a rare disease may be unable to wait to perform an experiment until all the experimental units are recruited. Our work offers a mathematical framework for sequential rerandomization designs, where the experimental units are enrolled in groups. We formulate an adaptive rerandomization procedure for balancing treatment/control assignments over some continuous or binary covariates, using Mahalanobis distance as the imbalance measure. We prove in our key result that given the same number of rerandomizations, in expected value, under certain mild assumptions, sequential rerandomization achieves better covariate balance than rerandomization at one time. [ABSTRACT FROM AUTHOR]

This article considers causal inference for treatment contrasts from a randomized experiment using potential outcomes in a finite population setting. Adopting a Neymanian repeated sampling approach that integrates such causal inference with finite population survey sampling, an inferential framework is developed for general mechanisms of assigning experimental units to multiple treatments. This framework extends classical methods by allowing the possibility of randomization restrictions and unequal replications. Novel conditions that are “milder” than strict additivity of treatment effects, yet permit unbiased estimation of the finite population sampling variance of any treatment contrast estimator, are derived. The consequences of departures from such conditions are also studied under the criterion of minimax bias, and a new justification for using the Neymanian conservative sampling variance estimator in experiments is provided. The proposed approach can readily be extended to the case of treatments with a general factorial structure. [ABSTRACT FROM AUTHOR]

Several statistical agencies have started to use multiply-imputed synthetic microdata to create public-use data in major surveys. The purpose of doing this is to protect the confidentiality of respondents' identities and sensitive attributes, while allowing standard complete-data analyses of microdata. A key challenge, faced by advocates of synthetic data, is demonstrating that valid statistical inferences can be obtained from such synthetic data for non-confidential questions. Large discrepancies between observed-data and synthetic-data analytic results for such questions may arise because of uncongeniality; that is, differences in the types of inputs available to the imputer, who has access to the actual data, and to the analyst, who has access only to the synthetic data. Here, we discuss a simple, but possibly canonical, example of uncongeniality when using multiple imputation to create synthetic data, which specifically addresses the choices made by the imputer. An initial, unanticipated but not surprising, conclusion is that non-confidential design information used to impute synthetic data should be released with the confidential synthetic data to allow users of synthetic data to avoid possible grossly conservative inferences. [ABSTRACT FROM AUTHOR]

For likelihood-based inferences from data with missing values, models are generally needed for both the data and the missing-data mechanism. However, modeling the mechanism can be challenging, and parameters are often poorly identified. Rubin in 1976 showed that for likelihood and Bayesian inference, sufficient conditions for ignoring the missing data mechanism are (a) the missing data are missing at random (MAR), in the sense that missingness does not depend on the missing values after conditioning on the observed data and (b) the parameters of the data model and the missingness mechanism are distinct, that is, there are no a priori ties, via parameter space restrictions or prior distributions, between these two sets of parameters. These conditions are sufficient but not always necessary, and they relate to the full vector of parameters of the data model. We propose definitions of partially MAR and ignorability for a subvector of the parameters of particular substantive interest, for direct likelihood/Bayesian and frequentist likelihood-based inference. We apply these definitions to a variety of examples. We also discuss conditioning on the pattern of missingness, as an alternative strategy for avoiding the need to model the missingness mechanism. [ABSTRACT FROM AUTHOR]

The wise use of statistical ideas in practice essentially requires some Bayesian thinking, in contrast to the classical rigid frequentist dogma. This dogma too often has seemed to influence the applications of statistics, even at agencies like the FDA. Greg Campbell was one of the most important advocates there for more nuanced modes of thought, especially Bayesian statistics. Because two brilliant statisticians, Ronald Fisher and Jerzy Neyman, are often credited with instilling the traditional frequentist approach in current practice, I argue that both men were actually seeking very Bayesian answers, and neither would have endorsed the rigid application of their ideas. [ABSTRACT FROM PUBLISHER]

Unreplicated factorial designs have been widely used in scientific and industrial settings, when it is important to distinguish “active” or real factorial effects from “inactive” or noise factorial effects used to estimate residual or “error” terms. We propose a new approach to screen for active factorial effects from such experiments that uses the potential outcomes framework and is based on sequential posterior predictive model checks. One advantage of the proposed method is its ability to broaden the standard definition of active effects and to link their definition to the population of interest. Another important aspect of this approach is its conceptual connection to Fisherian randomization tests. Extensive simulation studies are conducted, which demonstrate the superiority of the proposed approach over existing ones in the situations considered. [ABSTRACT FROM PUBLISHER]

Many empirical settings involve the specification of models leading to complicated likelihood functions, for example, finite mixture models that arise in causal inference when using Principal Stratification (PS). Traditional asymptotic results cannot be trusted for the associated likelihood functions, whose logarithms are not close to being quadratic and may be multimodal even with large sample sizes. We first investigate the shape of the likelihood function with models based on PS by providing diagnostic tools for evaluating ellipsoidal approximations based on the second derivatives of the log-likelihood at a mode. In these settings, inference based on standard approximations is inappropriate, and other forms of inference are required. We explore the use of a direct likelihood approach for parsimonious model selection and, specifically, propose comparing values of scaled maximized likelihood functions under competitive models to select preferred models. An extensive simulation study provides guidelines, for calibrating the use of scaled log-likelihood ratio statistics, as functions of the complexity of the models being compared. [ABSTRACT FROM AUTHOR]

In randomized experiments, the random assignment of units to treatment groups justifies many of the widely used traditional analysis methods for evaluating causal effects. Specifying subgroups of units for further examination after observing outcomes, however, may partially nullify any advantages of randomized assignment when data are analyzed naively. Some previous statistical literature has treated all post-hoc subgroup analyses homogeneously as entirely invalid and thus uninterpretable. The extent of the validity of such analyses and the factors that affect the degree of validity remain largely unstudied. Here, we describe a recent pharmaceutical case with First Amendment legal implications, in which post-hoc subgroup analyses played a pivotal and controversial role. Through Monte Carlo simulation, we show that post-hoc results that seem highly significant make dramatic movements toward insignificance after accounting for the subgrouping procedure presumably used. Finally, we propose a novel, randomization-based method that generates valid post-hoc subgroupp-values, provided we know exactly how the subgroups were constructed. If we do not know the exact subgrouping procedure, our method may still place helpful bounds on the significance level of estimated effects. This randomization-based approach allows us to evaluate causal effects in situations where valid evaluations were previously considered impossible. [Received February 2014. Revised April 2015.] [ABSTRACT FROM PUBLISHER]

We clarify the key concept of missingness at random in incomplete data analysis. We first distinguish between data being missing at random and the missingness mechanism being a missing-at-random one, which we call missing always at random and which is more restrictive.We further discuss how, in general, neither of these conditions is a statement about conditional independence.We then consider the implication of the more restrictive missing-always-at-random assumption when coupled with full unit-exchangeability for the matrix of the variables of interest and the missingness indicators: the conditional distribution of the missingness indicators for any variable that can have a missing value can depend only on variables that are always fully observed. We discuss implications of this for modelling missingness mechanisms. [ABSTRACT FROM AUTHOR]

When conducting a randomized experiment, if an allocation yields treatment groups that differ meaningfully with respect to relevant covariates, groups should be rerandomized. The process involves specifying an explicit criterion for whether an allocation is acceptable, based on a measure of covariate balance, and rerandomizing units until an acceptable allocation is obtained. Here, we illustrate how rerandomization could have improved the design of an already conducted randomized experiment on vocabulary and mathematics training programs, then provide a rerandomization procedure for covariates that vary in importance, and finally offer other extensions for rerandomization, including methods addressing computational efficiency. When covariates vary in a priori importance, better balance should be required for more important covariates. Rerandomization based on Mahalanobis distance preserves the joint distribution of covariates, but balances all covariates equally. Here, we propose rerandomizing based on Mahalanobis distance within tiers of covariate importance. Because balancing covariates in one tier will in general also partially balance covariates in other tiers, for each subsequent tier we explicitly balance only the components orthogonal to covariates in more important tiers. [ABSTRACT FROM AUTHOR]

Estimation of causal effects in non-randomized studies comprises two distinct phases: design, without outcome data, and analysis of the outcome data according to a specified protocol. Recently, Gutman and Rubin (2013) proposed a new analysis-phase method for estimating treatment effects when the outcome is binary and there is only one covariate, which viewed causal effect estimation explicitly as a missing data problem. Here, we extend this method to situations with continuous outcomes and multiple covariates and compare it with other commonly used methods (such as matching, subclassification, weighting, and covariance adjustment). We show, using an extensive simulation, that of all methods considered, and in many of the experimental conditions examined, our new 'multiple-imputation using two subclassification splines' method appears to be the most efficient and has coverage levels that are closest to nominal. In addition, it can estimate finite population average causal effects as well as non-linear causal estimands. This type of analysis also allows the identification of subgroups of units for which the effect appears to be especially beneficial or harmful. [ABSTRACT FROM AUTHOR]

By 'partially post-hoc' subgroup analyses, we mean analyses that compare existing data from a randomized experiment-from which a subgroup specification is derived-to new, subgroup-only experimental data. We describe a motivating example in which partially post hoc subgroup analyses instigated statistical debate about a medical device's efficacy. We clarify the source of such analyses' invalidity and then propose a randomization-based approach for generating valid posterior predictive p-values for such partially post hoc subgroups. Lastly, we investigate the approach's operating characteristics in a simple illustrative setting through a series of simulations, showing that it can have desirable properties under both null and alternative hypotheses. [ABSTRACT FROM AUTHOR]

Health and medical data are increasingly being generated, collected, and stored in electronic form in healthcare facilities and administrative agencies. Such data hold a wealth of information vital to effective health policy development and evaluation, as well as to enhanced clinical care through evidence-based practice and safety and quality monitoring. These initiatives are aimed at improving individuals' health and well-being. Nevertheless, analyses of health data archives must be conducted in such a way that individuals' privacy is not compromised. One important aspect of protecting individuals' privacy is protecting the confidentiality of their data. It is the purpose of this paper to provide a review of a number of approaches to reducing disclosure risk when making data available for research, and to present a taxonomy for such approaches. Some of these methods are widely used, whereas others are still in development. It is important to have a range of methods available because there is also a range of data-use scenarios, and it is important to be able to choose between methods suited to differing scenarios. In practice, it is necessary to find a balance between allowing the use of health and medical data for research and protecting confidentiality. This balance is often presented as a trade-off between disclosure risk and data utility, because methods that reduce disclosure risk, in general, also reduce data utility. Copyright © 2015 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

A framework for causal inference from two-level factorial designs is proposed, which uses potential outcomes to define causal effects. The paper explores the effect of non-additivity of unit level treatment effects on Neyman's repeated sampling approach for estimation of causal effects and on Fisher's randomization tests on sharp null hypotheses in these designs. The framework allows for statistical inference from a finite population, permits definition and estimation of estimands other than 'average factorial effects' and leads to more flexible inference procedures than those based on ordinary least squares estimation from a linear model. [ABSTRACT FROM AUTHOR]

We analyze publicly available data to estimate the causal effects of military interventions on the homicide rates in certain problematic regions in Mexico. We use the Rubin causal model to compare the post-intervention homicide rate in each intervened region to the hypothetical homicide rate for that same year had the military intervention not taken place. Because the effect of a military intervention is not confined to the municipality subject to the intervention, a nonstandard definition of units is necessary to estimate the causal effect of the intervention under the standard no-interference assumption of stable-unit treatment value assumption (SUTVA). Donor pools are created for each missing potential outcome under no intervention, thereby allowing for the estimation of unit-level causal effects. A multiple imputation approach accounts for uncertainty about the missing potential outcomes. [ABSTRACT FROM AUTHOR]