Article

Instruments for Causal Inference: An Epidemiologist's Dream?

Department of Epidemiology, Harvard School of Public Health, Boston, Massachusetts 02115, USA.
Epidemiology (Impact Factor: 6.18). 08/2006; 17(4):360-72. DOI: 10.1097/01.ede.0000222409.00878.37
Source: PubMed

ABSTRACT 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.

1 Follower
 · 
203 Views
  • 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.
  • Source
    • "This is done out of necessity, for example, we cannot measure the actual preference of the physician when using a preference-based instrument, or we sometimes only have the means to measure approximate locations in the genome when using a genetic-based instrument. Although the use of such a noncausal instrument could satisfy the other identifying assumptions, this measurement error complicates our interpretation of a LATE-like effect (Hernán and Robins, 2006). "
    [Show abstract] [Hide abstract]
    ABSTRACT: Discussion of "Instrumental Variables: An Econometrician's Perspective" by Guido W. Imbens [arXiv:1410.0163].
    Statistical Science 10/2014; 29(3). DOI:10.1214/14-STS491 · 1.69 Impact Factor
  • Source
    • "In fact, unlike Figure 1, a genetic variant used in a Mendelian randomization analysis need not necessarily be causally related to the exposure; it may be a proxy for the true causal variant. Any variant in linkage disequilibrium (meaning correlated in its distribution) with the causal variant which satisfies the IV assumptions can be used as an IV [7]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: b>Background: Mendelian randomization uses genetic variants, assumed to be instrumental variables for a particular exposure, to estimate the causal effect of that exposure on an outcome. If the instrumental variable criteria are satisfied, the resulting estimator is consistent even in the presence of unmeasured confounding and reverse causation. Methods: We extend the Mendelian randomization paradigm to investigate more complex networks of relationships between variables, in particular where some of the effect of an exposure on the outcome may operate through an intermediate variable (a mediator). If instrumental variables for the exposure and mediator are available, direct and indirect effects of the exposure on the outcome can be estimated, for example using either a regression-based method or structural equation models. The direction of effect between the exposure and a possible mediator can also be assessed. Methods are illustrated in an applied example considering causal relationships between body mass index, C-reactive protein and uric acid. Results: These estimators are consistent in the presence of unmeasured confounding if, in addition to the instrumental variable assumptions, the effects of both the exposure on the mediator and the mediator on the outcome are homogeneous across individuals and linear without interactions. Nevertheless, a simulation study demonstrates that even considerable heterogeneity in these effects does not lead to bias in the estimates. Conclusions: These methods can be used to estimate direct and indirect causal effects in a mediation setting, and have potential for the investigation of more complex networks between multiple interrelated exposures and disease outcomes.
    International Journal of Epidemiology 08/2014; DOI:10.1093/ije/dyu176 · 9.20 Impact Factor
Show more

Preview

Download
3 Downloads