Instruments for Causal Inference: An Epidemiologist's Dream?

Department of Epidemiology, Harvard School of Public Health, Boston, Massachusetts 02115, USA.
Epidemiology (Impact Factor: 6.2). 08/2006; 17(4):360-72. DOI: 10.1097/01.ede.0000222409.00878.37
Source: PubMed


The use of instrumental variable (IV) methods is attractive because, even in the presence of unmeasured confounding, such methods may consistently estimate the average causal effect of an exposure on an outcome. However, for this consistent estimation to be achieved, several strong conditions must hold. We review the definition of an instrumental variable, describe the conditions required to obtain consistent estimates of causal effects, and explore their implications in the context of a recent application of the instrumental variables approach. We also present (1) a description of the connection between 4 causal models-counterfactuals, causal directed acyclic graphs, nonparametric structural equation models, and linear structural equation models-that have been used to describe instrumental variables methods; (2) a unified presentation of IV methods for the average causal effect in the study population through structural mean models; and (3) a discussion and new extensions of instrumental variables methods based on assumptions of monotonicity.

  • Source
    • "Our discussion of bounding the per-protocol effect focused on dichotomous outcomes and point interventions . Similar bounds under the instrumental conditions can be identified for continuous outcomes if one assumes the outcomes are finitely bounded[8], and the point-identification expressions under effect homogeneity conditions can also be restated to apply to continuous outcomes[6,7,16]. Because we can choose to estimate cumulative risk up through any point in time in follow-up, we could also extend these bounds to bounding the survival curve for time-to-event outcomes[18]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Background The per-protocol effect is the effect that would have been observed in a randomized trial had everybody followed the protocol. Though obtaining a valid point estimate for the per-protocol effect requires assumptions that are unverifiable and often implausible, lower and upper bounds for the per-protocol effect may be estimated under more plausible assumptions. Strategies for obtaining bounds, known as “partial identification” methods, are especially promising in randomized trials. Results We estimated bounds for the per-protocol effect of colorectal cancer screening in the Norwegian Colorectal Cancer Prevention trial, a randomized trial of one-time sigmoidoscopy screening in 98,792 men and women aged 50–64 years. The screening was not available to the control arm, while approximately two thirds of individuals in the treatment arm attended the screening. Study outcomes included colorectal cancer incidence and mortality over 10 years of follow-up. Without any assumptions, the data alone provide little information about the size of the effect. Under the assumption that randomization had no effect on the outcome except through screening, a point estimate for the risk under no screening and bounds for the risk under screening are achievable. Thus, the 10-year risk difference for colorectal cancer was estimated to be at least −0.6 % but less than 37.0 %. Bounds for the risk difference for colorectal cancer mortality (–0.2 to 37.4 %) and all-cause mortality (–5.1 to 32.6 %) had similar widths. These bounds appear helpful in quantifying the maximum possible effectiveness, but cannot rule out harm. By making further assumptions about the effect in the subpopulation who would not attend screening regardless of their randomization arm, narrower bounds can be achieved. Conclusions Bounding the per-protocol effect under several sets of assumptions illuminates our reliance on unverifiable assumptions, highlights the range of effect sizes we are most confident in, and can sometimes demonstrate whether to expect certain subpopulations to receive more benefit or harm than others. Trial registration identifier NCT00119912 (registered 6 July 2005) Electronic supplementary material The online version of this article (doi:10.1186/s13063-015-1056-8) contains supplementary material, which is available to authorized users.
    Full-text · Article · Dec 2015 · Trials
  • Source
    • "The use of genetic variants as instrumental variables in observational data has been termed 'Mendelian randomization' [6] [7]. Many reviews exist on the use of instrumental variables, in particular on the assumptions necessary to be an instrumental variable [8] [9], assessing the validity of instrumental variables [10], assumptions necessary for estimation of a causal effect parameter using instrumental variables [11] [12] [13], methods for effect estimation with multiple instrumental variables [14], with binary outcomes [15] [16], methods for the estimation of odds ratios [17], and guidelines for the reporting of instrumental variable analysis [18]. We seek to complement this literature by contributing a review to compare methods for instrumental variable analysis, with accompanying practical guidelines on their use. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Instrumental variable analysis is an approach for obtaining causal inferences on the effect of an exposure (risk factor) on an outcome from observational data. It has gained in popularity over the past decade with the use of genetic variants as instrumental variables, known as Mendelian randomization. An instrumental variable is associated with the exposure, but not associated with any confounder of the exposure-outcome association, nor is there any causal pathway from the instrumental variable to the outcome other than via the exposure. Under the assumption that a single instrumental variable or a set of instrumental variables for the exposure is available, the causal effect of the exposure on the outcome can be estimated. There are several methods available for instrumental variable estimation; we consider the ratio method, two-stage methods, likelihood-based methods, and semi-parametric methods. Techniques for obtaining statistical inferences and confidence intervals are presented. The statistical properties of estimates from these methods are compared, and practical advice is given about choosing a suitable analysis method. In particular, bias and coverage properties of estimators are considered, especially with weak instruments. Settings particularly relevant to Mendelian randomization are prioritized in the paper, notably the scenario of a continuous exposure and a continuous or binary outcome. © The Author(s) 2015.
    Full-text · Article · Jul 2015 · Statistical Methods in Medical Research
  • Source
    • "Intuitively, the IV method seeks to extract variation in treatment that is free of unmeasured confounders and uses this variation to estimate the treatment effect. For more information on IV methods, see Angrist et al. (1996), Newhouse and McClellan (1998), Greenland (2000), Hernán and Robins (2006), Cheng et al. (2009a), Baiocchi et al. (2014) and Imbens (2014). This paper is motivated by provider preference IV (PP IV) which is commonly used as an IV in health studies . "
    [Show abstract] [Hide abstract]
    ABSTRACT: Instrumental variable (IV) methods are widely used to adjust for the bias in estimating treatment effects caused by unmeasured confounders in observational studies. In this manuscript, we provide empirical and theoretical evidence that the IV methods may result in biased treatment effects if applied on a data set in which subjects are preselected based on their received treatments. We frame this as a selection bias problem and propose a procedure that identifies the treatment effect of interest as a function of a vector of sensitivity parameters. We also list assumptions under which analyzing the preselected data does not lead to a biased treatment effect estimate. The performance of the proposed method is examined using simulation studies. We applied our method on The Health Improvement Network (THIN) database to estimate the comparative effect of metformin and sulfonylureas on weight gain among diabetic patients.
    Preview · Article · Feb 2015
Show more