Preference-based instrumental variable methods for the estimation of treatment effects: assessing validity and interpreting results.

Division of Pharmacoepidemiology and Pharmacoeconomics, Brigham and Women's Hospital & Harvard Medical School, Boston, MA, USA.
The International Journal of Biostatistics (Impact Factor: 1.28). 02/2007; 3(1):Article 14. DOI: 10.2202/1557-4679.1072
Source: PubMed

ABSTRACT Observational studies of drugs and medical procedures based on administrative data are increasingly used to inform regulatory and clinical decisions. However, the validity of such studies is often questioned because available data may not contain measurements of many important prognostic variables that guide treatment decisions. Recently, approaches to this problem have been proposed that use instrumental variables (IV) defined at the level of an individual health care provider or aggregation of providers. Implicitly, these approaches attempt to estimate causal effects by using differences in medical practice patterns as a quasi-experiment. Although preference-based IV methods may usefully complement standard statistical approaches, they make assumptions that are unfamiliar to most biomedical researchers and therefore the validity of such analyses can be hard to evaluate. Here, we propose a simple framework based on a single unobserved dichotomous variable that can be used to explore how violations of IV assumptions and treatment effect heterogeneity may bias the standard IV estimator with respect to the average treatment effect in the population. This framework suggests various ways to anticipate the likely direction of bias using both empirical data and commonly available subject matter knowledge, such as whether medications or medical procedures tend to be overused, underused, or often misused. This approach is described in the context of a study comparing the gastrointestinal bleeding risk attributable to different non-steroidal anti-inflammatory drugs.

  • [Show abstract] [Hide abstract]
    ABSTRACT: Background-Compared with transfemoral access, transradial access (TRA) for percutaneous coronary intervention is associated with reduced risk of bleeding and vascular complications. Studies suggest that TRA may reduce mortality in patients with ST-segment-elevation myocardial infarction. However, there are few data on the effect of TRA on mortality, specifically, in patients with non-ST-segment-elevation myocardial infarction. Methods and Results-We analyzed 10 095 consecutive patients with non-ST-segment-elevation myocardial infarction treated with percutaneous coronary intervention between 2005 and 2011 in all 8 tertiary cardiac centers in London, United Kingdom. TRA was a predictor for reduced bleeding (odds ratio=0.21; 95% confidence interval [CI]: 0.08-0.57; P=0.002), access-site complications (odds ratio=0.47; 95% CI: 0.23-0.95; P=0.034), and 1-year mortality (hazard ratio [HR]=0.72; 95% CI: 0.54-0.94; P=0.017). Between 2005 and 2007, TRA did not appear to reduce mortality at 1 year (HR=0.81; 95% CI: 0.51-1.28; P=0.376), whereas between 2008 and 2011, TRA conferred survival benefit at 1 year (HR=0.65; 95% CI: 0.46-0.92; P=0.015). The mortality benefit with TRA at 1 year was not seen at the low-volume centers (HR=0.80; 95% CI: 0.47-1.38; P=0.428) but specifically seen in the high volume radial centers (HR=0.70; 95% CI: 0.51-0.97; P=0.031). In propensity-matched analyses, TRA remained a predictor for survival at 1 year (HR=0.60; 95% CI: 0.42-0.85; P=0.005). Instrumental variable analysis demonstrated that TRA conferred mortality benefit at 1-year with an absolute mortality reduction of 5.8% (P=0.039). Conclusions-In this analysis of patients with non-ST-segment-elevation myocardial infarction, TRA appears to be a predictor for survival. Furthermore, the evolving learning curve, experience, and expertise may be important factors contributing to the prognostic benefit conferred with TRA.
    Circulation Cardiovascular Interventions 06/2014; 7(4). DOI:10.1161/CIRCINTERVENTIONS.114.001314 · 6.98 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Most previous studies of the causal relationship between malaria and stunting have been studies where potential confounders are controlled via regression-based methods, but these studies may have been biased by unobserved confounders. Instrumental variables (IV) regression offers a way to control for unmeasured confounders where, in our case, the sickle cell trait can be used as an instrument. However, for the instrument to be valid, it may still be important to account for measured confounders. The most commonly used instrumental variable regression method, two-stage least squares, relies on parametric assumptions on the effects of measured confounders to account for them. Additionally, two-stage least squares lacks transparency with respect to covariate balance and weighing of subjects and does not blind the researcher to the outcome data. To address these drawbacks, we propose an alternative method for IV estimation based on full matching. We evaluate our new procedure on simulated data and real data concerning the causal effect of malaria on stunting among children. We estimate that the risk of stunting among children with the sickle cell trait decrease by 0.22 times the average number of malaria episodes prevented by the sickle cell trait, a substantial effect of malaria on stunting (p-value: 0.011, 95% CI: 0.044, 1).
  • [Show abstract] [Hide abstract]
    ABSTRACT: Instrumental variable (IV) methods are increasingly being used in comparative effectiveness research. Studies using these methods often compare 2 particular treatments, and the researchers perform their IV analyses conditional on patients' receiving this subset of treatments (while ignoring the third option of "neither treatment"). The ensuing selection bias that occurs due to this restriction has gone relatively unnoticed in interpretations and discussions of these studies' results. In this paper we describe the structure of this selection bias with examples drawn from commonly proposed instruments such as calendar time and preference, illustrate the bias with causal diagrams, and estimate the magnitude and direction of possible bias using simulations. A noncausal association between the proposed instrument and the outcome can occur in analyses restricted to patients receiving a subset of the possible treatments. This results in bias in the numerator for the standard IV estimator; the bias is amplified in the treatment effect estimate. The direction and magnitude of the bias in the treatment effect estimate are functions of the distribution of and relationships between the proposed instrument, treatment values, unmeasured confounders, and outcome. IV methods used to compare a subset of treatment options are prone to substantial biases, even when the proposed instrument appears relatively strong. © The Author 2015. Published by Oxford University Press on behalf of the Johns Hopkins Bloomberg School of Public Health. All rights reserved. For permissions, please e-mail:


Available from