An Approach for Estimating Causal Effects in Randomized Trials with Noncompliance

We developed methods for estimating the causal risk difference and causal risk ratio in randomized trials with noncompliance. The developed estimator is unbiased under the assumption that biases due to noncompliance are identical between both treatment arms. The biases are defined as the difference or ratio between the expectations of potential outcomes for a group that received the test treatment and that for the control group in each randomly assigned group. Although the instrumental variable estimator yields an unbiased estimate under a sharp null hypothesis but may yield a biased estimate under a non-null hypothesis, the bias of the developed estimator does not depend on whether this hypothesis holds. Then the estimate of the causal effect from the developed estimator may have a smaller bias than that from the instrumental variable estimator when the treatment effect exists. There is not yet a standard method for coping with noncompliance, and thus it is important to evaluate estimates under different assumptions. The developed estimator can serve this purpose. Its application to a field trial for coronary heart disease is provided.     

Criteria for surrogate end points based on causal distributions

Summary.  When a treatment has a positive average causal effect (ACE) on an intermediate variable or surrogate end point which in turn has a positive ACE on a true end point, the treatment may have a negative ACE on the true end point due to the presence of unobserved confounders, which is called the surrogate paradox. A criterion for surrogate end points based on ACEs has recently been proposed to avoid the surrogate paradox. For a continuous or ordinal discrete end point, the distributional causal effect (DCE) may be a more appropriate measure for a causal effect than the ACE. We discuss criteria for surrogate end points based on DCEs. We show that commonly used models, such as generalized linear models and Cox's proportional hazard models, can make the sign of the DCE of the treatment on the true end point determinable by the sign of the DCE of the treatment on the surrogate even if the models include unobserved confounders. Furthermore, for a general distribution without any assumption of parametric models, we give a sufficient condition for a distributionally consistent surrogate and prove that it is almost necessary.     

Estimation of Causal Effects in Latent Strata with an Encouragement for Response

We consider a new approach to deal with non ignorable non response on an outcome variable, in a causal inference framework. Assuming that a binary instrumental variable for non response is available, we provide a likelihood-based approach to identify and estimate heterogeneous causal effects of a binary treatment on specific latent subgroups of units, named principal strata, defined by the non response behavior under each level of the treatment and of the instrument. We show that, within each stratum, non response is ignorable and respondents can be properly compared by treatment status. In order to assess our method and its robustness when the usually invoked assumptions are relaxed or misspecified, we simulate data to resemble a real experiment conducted on a panel survey which compares different methods of reducing panel attrition.     

Identification and Inference With Many Invalid Instruments

We study estimation and inference in settings where the interest is in the effect of a potentially endogenous regressor on some outcome. To address the endogeneity, we exploit the presence of additional variables. Like conventional instrumental variables, these variables are correlated with the endogenous regressor. However, unlike conventional instrumental variables, they also have direct effects on the outcome, and thus are “invalid” instruments. Our novel identifying assumption is that the direct effects of these invalid instruments are uncorrelated with the effects of the instruments on the endogenous regressor. We show that in this case the limited-information-maximum-likelihood (liml) estimator is no longer consistent, but that a modification of the bias-corrected two-stage-least-square (tsls) estimator is consistent. We also show that conventional tests for over-identifying restrictions, adapted to the many instruments setting, can be used to test for the presence of these direct effects. We recommend that empirical researchers carry out such tests and compare estimates based on liml and the modified version of bias-corrected tsls. We illustrate in the context of two applications that such practice can be illuminating, and that our novel identifying assumption has substantive empirical content.     

我国正规就业者的教育收益率

针对教育收益率测算中可能存在的弱工具变量问题,本文利用2006年中国健康与营养调查数据,结合工具变量估计框架下的各种模型设定检验,对我国正规就业者的教育收益率进行测算。检验和测算结果表明：受教育程度的变量存在内生性,个体配偶的受教育年限是内生变量受教育程度的强工具变量,而个体的出生季度是弱工具变量。广义矩估计结果显示我国正规就业者的教育收益率为10.1%。     

Investigation about a screening step in model selection

In many studies a large number of variables is measured and the identification of relevant variables influencing an outcome is an important task. For variable selection several procedures are available. However, focusing on one model only neglects that there usually exist other equally appropriate models. Bayesian or frequentist model averaging approaches have been proposed to improve the development of a predictor. With a larger number of variables (say more than ten variables) the resulting class of models can be very large. For Bayesian model averaging Occam’s window is a popular approach to reduce the model space. As this approach may not eliminate any variables, a variable screening step was proposed for a frequentist model averaging procedure. Based on the results of selected models in bootstrap samples, variables are eliminated before deriving a model averaging predictor. As a simple alternative screening procedure backward elimination can be used. Through two examples and by means of simulation we investigate some properties of the screening step. In the simulation study we consider situations with fifteen and 25 variables, respectively, of which seven have an influence on the outcome. With the screening step most of the uninfluential variables will be eliminated, but also some variables with a weak effect. Variable screening leads to more applicable models without eliminating models, which are more strongly supported by the data. Furthermore, we give recommendations for important parameters of the screening step.     

Modified SEE variable selection for varying coefficient instrumental variable models

We consider the problem of variable selection for a class of varying coefficient models with instrumental variables. We focus on the case that some covariates are endogenous variables, and some auxiliary instrumental variables are available. An instrumental variable based variable selection procedure is proposed by using modified smooth-threshold estimating equations (SEEs). The proposed procedure can automatically eliminate the irrelevant covariates by setting the corresponding coefficient functions as zero, and simultaneously estimate the nonzero regression coefficients by solving the smooth-threshold estimating equations. The proposed variable selection procedure avoids the convex optimization problem, and is flexible and easy to implement. Simulation studies are carried out to assess the performance of the proposed variable selection method.     

Computational procedures for deriving sampling distributions of attribute-contaminated random variables

Statistical distributions generated from any J- or U-shaped random variables are cumbersome to derive if not completely indefinable and thus are unavailable analytically because of the singularities at the tails of the basic random variable. This paper presents a computational method for providing a numerical convolution derived from a basic U-shaped random variable composed of a continuous part mixed with (or contaminated by) a discrete part at the tails. The J-shaped sampling distribution case is implied as a special case. Though the computations are based on a background Normal Distribution, it can be generalized on any other distribution.Such distributions will open up an area of sampling distributions of mixed random variables that are not elaborately covered in textbooks dealing with the theory of distributions.     

Estimating a Marginal Causal Odds Ratio Subject to Confounding

Odds ratios are frequently used to describe the relationship between a binary treatment or exposure and a binary outcome. An odds ratio can be interpreted as a causal effect or a measure of association, depending on whether it involves potential outcomes or the actual outcome. An odds ratio can also be characterized as marginal versus conditional, depending on whether it involves conditioning on covariates. This article proposes a method for estimating a marginal causal odds ratio subject to confounding. The proposed method is based on a logistic regression model relating the outcome to the treatment indicator and potential confounders. Simulation results show that the proposed method performs reasonably well in moderate-sized samples and may even offer an efficiency gain over the direct method based on the sample odds ratio in the absence of confounding. The method is illustrated with a real example concerning coronary heart disease.     

Robust, accurate confidence intervals with a weak instrument: quarter of birth and education

Summary.  An instrument or instrumental variable manipulates a treatment and affects the outcome only indirectly through its manipulation of the treatment. For instance, encouragement to exercise might increase cardiovascular fitness, but only indirectly to the extent that it increases exercise. If instrument levels are randomly assigned to individuals, then the instrument may permit consistent estimation of the effects caused by the treatment, even though the treatment assignment itself is far from random. For instance, one can conduct a randomized experiment assigning some subjects to 'encouragement to exercise' and others to 'no encouragement' but, for reasons of habit or taste, some subjects will not exercise when encouraged and others will exercise without encouragement; none-the-less, such an instrument aids in estimating the effect of exercise. Instruments that are weak, i.e. instruments that have only a slight effect on the treatment, present inferential problems. We evaluate a recent proposal for permutation inference with an instrumental variable in four ways: using Angrist and Krueger's data on the effects of education on earnings using quarter of birth as an instrument, following Bound, Jaeger and Baker in using simulated independent observations in place of the instrument in Angrist and Krueger's data, using entirely simulated data in which correct answers are known and finally using statistical theory to show that only permutation inferences maintain correct coverage rates. The permutation inferences perform well in both easy and hard cases, with weak instruments, as well as with long-tailed responses.     

Examples of Decompositions of Chi-Squared Variables

Two examples of absolutely continuous bivariate distributions are given. The first example illustrates the fact that the sum of two random variables can be χ², one of the variables χ², the other variable positive but not necessarily χ². The second example illustrates the fact that the sum of the variables can be χ², each variable can be χ², the degrees of freedom add up properly but the two variables need not be independent.     

Testing parameter significance in instrumental variables probit estimators: some simulation

Binary choice models that contain endogenous regressors can now be estimated routinely using modern software. Each of the two packages, Stata 11 [Stata Statistical Software: Release 11, StataCorp LP, College Station, TX, 2009] and Limdep 9 [Econometric Software Inc., Plainview, NY, 2008], contains two estimators that can be used to estimate such a model. This paper compares the performance of maximum likelihood, Newey's Amemiya's generalized least-squares (AGLS) estimator, an instrumental variables plug-in estimator and others in samples of sizes 200 and 1000 using simulation. Specifically, this paper focuses on tests of parameter significance under various degrees of instrument strength and severity of endogeneity. Although the maximum-likelihood estimator performs well in large samples, there is some evidence that the more computationally robust AGLS estimator may perform better in smaller samples when instruments are weak. It also appears that instruments in endogenous probit estimation need to be even stronger than when used in linear instrumental variables (IV) estimation.     

Covariate selection for estimating the causal effect of control plans by using causal diagrams

Summary. Consider a case where cause–effect relationships between variables can be described by a causal path diagram and the corresponding linear structural equation model. The paper proposes a graphical selection criterion for covariates to estimate the causal effect of a control plan. For designing the control plan, it is essential to determine both covariates that are used for control and covariates that are used for identification. The selection of covariates used for control is only constrained by the requirement that the covariates be non-descendants of a treatment variable. However, the selection of covariates used for identification is dependent on the selection of covariates used for control and is not unique. In the paper, the difference between covariates that are used for identification is evaluated on the basis of the asymptotic variance of the estimated causal effect of an effective control plan. Furthermore, the results can be also described in terms of a graph structure.     

CORRECTING FOR MEASUREMENT ERROR IN AN EXPOSURE-RESPONSE RELATIONSHIP BASED ON DICHOTOMISING A CONTINUOUS DEPENDENT VARIABLE

Random error in a continuous outcome variable does not affect its regression on a predictor. However, when a continuous outcome variable is dichotomised, random measurement error results in a flatter exposure-response relationship with a higher intercept. Although this consequence is similar to the effect of misclassification in a binary outcome variable, it cannot be corrected using techniques appropriate for binary data. Conditional distributions of the measurements of the continuous outcome variable can be corrected if the reliability coefficient of the measurements can be estimated. An unbiased estimate of the exposure-response relationship is then easily calculated. This procedure is demonstrated using data on the relationship between smoking and the development of airway obstruction.     

Controlled Direct and Mediated Effects: Definition,Identification and Bounds

Abstract. Results are given which provide bounds for controlled direct effects when nounmeasured confounding assumptions required for the identification of these effects do not hold. Previous results concerning bounds for controlled direct effects rely on monotonicity relationships between the treatment, mediator and the outcome themselves; the results presented in this article instead assume that monotonicity relationships hold between the unmeasured confounding variable or variables and the treatment, mediator and outcome. Whereas prior results give bounds that contain the null hypothesis of no direct effect, the results presented here will in many instances yield bounds that do not contain the null hypothesis of no direct effect. For contexts in which a set of variables intercepts all paths between a treatment and an outcome, it is possible to provide a definition for a controlled mediated effect. We discuss the identification of these controlled mediated effects; the bounds for controlled direct effects are applicable also to controlled mediated effects. An example is given to illustrate how the results in the article can be used to draw inferences about direct and mediated effects in the presence of unmeasured confounding variables.     

Semiparametric estimation and inference for distributional and general treatment effects

Summary.  There is a large literature on methods of analysis for randomized trials with noncompliance which focuses on the effect of treatment on the average outcome. The paper considers evaluating the effect of treatment on the entire distribution and general functions of this effect. For distributional treatment effects, fully non-parametric and fully parametric approaches have been proposed. The fully non-parametric approach could be inefficient but the fully parametric approach is not robust to the violation of distribution assumptions. We develop a semiparametric instrumental variable method based on the empirical likelihood approach. Our method can be applied to general outcomes and general functions of outcome distributions and allows us to predict a subject's latent compliance class on the basis of an observed outcome value in observed assignment and treatment received groups. Asymptotic results for the estimators and likelihood ratio statistic are derived. A simulation study shows that our estimators of various treatment effects are substantially more efficient than the currently used fully non-parametric estimators. The method is illustrated by an analysis of data from a randomized trial of an encouragement intervention to improve adherence to prescribed depression treatments among depressed elderly patients in primary care practices.     

A simpler approach for mediation analysis for dichotomous mediators in logistic regression

Mediation is a hypothesized causal chain among three variables. Mediation analysis for continuous response variables is well developed in the literature, and it can be shown that the indirect effect is equal to the total effect minus the direct effect. However, mediation analysis for categorical responses is still not fully developed. The purpose of this article is to propose a simpler method of analysing the mediation effect among three variables when the dependent and mediator variables are both dichotomous. We propose using the latent variable technique which in turn will adjust for the necessary condition that indirect effect is equal to the total effect minus the direct effect. An intensive simulation study is conducted to compare the proposed method with other methods in the literature. Our theoretical derivation and simulation study show that the proposed approach is simpler to use and at least as good as other approaches provided in the literature. We illustrate our approach to test for the potential mediators on the relationship between depression and obesity among children and adolescents compared to the method in Winship and Mare using National children health survey data 2011–2012.     

Instrumental variable estimation in ordinal probit models with mismeasured predictors

Researchers in the medical, health, and social sciences routinely encounter ordinal variables such as self‐reports of health or happiness. When modelling ordinal outcome variables, it is common to have covariates, for example, attitudes, family income, retrospective variables, measured with error. As is well known, ignoring even random error in covariates can bias coefficients and hence prejudice the estimates of effects. We propose an instrumental variable approach to the estimation of a probit model with an ordinal response and mismeasured predictor variables. We obtain likelihood‐based and method of moments estimators that are consistent and asymptotically normally distributed under general conditions. These estimators are easy to compute, perform well and are robust against the normality assumption for the measurement errors in our simulation studies. The proposed method is applied to both simulated and real data. The Canadian Journal of Statistics 47: 653–667; 2019 © 2019 Statistical Society of Canada     

Copula regression spline models for binary outcomes

We introduce a framework for estimating the effect that a binary treatment has on a binary outcome in the presence of unobserved confounding. The methodology is applied to a case study which uses data from the Medical Expenditure Panel Survey and whose aim is to estimate the effect of private health insurance on health care utilization. Unobserved confounding arises when variables which are associated with both treatment and outcome are not available (in economics this issue is known as endogeneity). Also, treatment and outcome may exhibit a dependence which cannot be modeled using a linear measure of association, and observed confounders may have a non-linear impact on the treatment and outcome variables. The problem of unobserved confounding is addressed using a two-equation structural latent variable framework, where one equation essentially describes a binary outcome as a function of a binary treatment whereas the other equation determines whether the treatment is received. Non-linear dependence between treatment and outcome is dealt using copula functions, whereas covariate-response relationships are flexibly modeled using a spline approach. Related model fitting and inferential procedures are developed, and asymptotic arguments presented.     

Partial identification of average treatment effects on the treated through difference-in-differences

ABSTRACT

The difference-in-differences (DID) method is widely used as a tool for identifying causal effects of treatments in program evaluation. When panel data sets are available, it is well-known that the average treatment effect on the treated (ATT) is point-identified under the DID setup. If a panel data set is not available, repeated cross sections (pretreatment and posttreatment) may be used, but may not point-identify the ATT. This paper systematically studies the identification of the ATT under the DID setup when posttreatment treatment status is unknown for the pretreatment sample. This is done through a novel application of an extension of a continuous version of the classical monotone rearrangement inequality which allows for general copula bounds. The identifying power of an instrumental variable and of a ‘matched subsample’ is also explored. Finally, we illustrate our approach by estimating the effect of the Americans with Disabilities Act of 1991 on employment outcomes of the disabled.