Causal Inference in Hybrid Intervention Trials Involving Treatment Choice

Journal of the American Statistical Association (Impact Factor: 1.98). 06/2008; 103(June):474-484. DOI: 10.2307/27640072
Source: RePEc


Although the randomized, controlled trial (RCT) is considered the gold standard in research for determining the efficacy of health education interventions, such trials may be vulnerable to "preference effects"; that is, differential outcomes depending on whether an individual is randomized to his or her preferred treatment. In this study, we review theoretical and empirical literature regarding designs that account for such effects in medical research, and consider the appropriateness of these designs to health education research. To illustrate the application of a preference design to health education research, we present analyses using process data from a mixed RCT/preference trial comparing two formats (Group or Self-Directed) of the "Women take PRIDE" heart disease management program. Results indicate that being able to choose one's program format did not significantly affect the decision to participate in the study. However, women who chose the Group format were over 4 times as likely to attend at least one class and were twice as likely to attend a greater number of classes than those who were randomized to the Group format. Several predictors of format preference were also identified, with important implications for targeting disease-management education to this population.

Download full-text


Available from: Roderick J Little,
  • Source
    • "The WTP study utilized a Doubly Randomized Preference Trial (DRPT) design (Long et al. 2008), where some participants are randomized to a treatment in a random arm and some are allowed to choose their treatments in a choice arm. The design is discussed in detail by Long et al. (2008). The random arm is a typical three-arm randomized trial and is the primary motivation for our work. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Data analysis for randomized trials including multi-treatment arms is often complicated by subjects who do not comply with their treatment assignment. We discuss here methods of estimating treatment efficacy for randomized trials involving multi-treatment arms subject to non-compliance. One treatment effect of interest in the presence of non-compliance is the complier average causal effect (CACE) (Angrist et al. 1996), which is defined as the treatment effect for subjects who would comply regardless of the assigned treatment. Following the idea of principal stratification (Frangakis & Rubin 2002), we define principal compliance (Little et al. 2009) in trials with three treatment arms, extend CACE and define causal estimands of interest in this setting. In addition, we discuss structural assumptions needed for estimation of causal effects and the identifiability problem inherent in this setting from both a Bayesian and a classical statistical perspective. We propose a likelihood-based framework that models potential outcomes in this setting and a Bayes procedure for statistical inference. We compare our method with a method of moments approach proposed by Cheng & Small (2006) using a hypothetical data set, and further illustrate our approach with an application to a behavioral intervention study (Janevic et al. 2003).
    Applied Statistics 05/2010; 59(3):513-531. DOI:10.1111/j.1467-9876.2009.00709.x · 1.49 Impact Factor
  • Source
    • "There are pros and cons with each hybrid design (West et al., 2008). However, it is important to note that these designs will allow us to estimate the preference effect and the impact of this effect on treatment outcome, which we cannot obtain from a classical RCT (Long et al., 2008). "
    [Show abstract] [Hide abstract]
    ABSTRACT: Exercise is an adjunct intervention for treating osteoarthritis (OA) knee pain, but many older adults, especially those with cognitive impairment, refuse to participate because of their frailty. Tai chi is a gentle alternative to Western-style aerobic exercise. In this article, we report recruitment experiences based on older adults' comments and on staff's observations and reports in a pilot randomized controlled trial (RCT) using tai chi as an intervention to reduce OA knee pain in a population of older adults with cognitive impairment. Recruitment challenges included issues with retirement apartment site staff, the older adults, study criteria or study design, and insufficient research staff. Strategies included networking and staying connected with site staff, using various recruiting approaches, providing incentives/motivation, and using informal leaders or residents as a way to recruit participants. Finally, modifying strict study criteria, securing staff for recruiting, and considering alternative designs to the classical RCT can also help overcome recruitment challenges.
    Research in Gerontological Nursing 10/2009; 2(4):228-34. DOI:10.3928/19404921-20090731-03 · 0.64 Impact Factor
  • Source
    • "In particular , the NSBR assumption is questionable when there are individuals who would participate in a study if allowed to choose their treatment but would not if they were randomized to treatment . In their section 7, Long et al. (2008) discussed generalizations of DRPT's that allow identification of parameters when these assumptions are relaxed. This material might serve as a useful framework for additional work on hybrid trials, which we believe to be a fruitful area for future study design. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Empirical researchers commonly invoke instrumental variable (IV) assumptions to identify treatment effects. This paper considers what can be learned under two specific violations of those assumptions: contaminated and corrupted data. Either of these violations prevents point identification, but sharp bounds of the treatment effect remain feasible. In an applied example, random miscarriages are an IV for women’s age at first birth. However, the inability to separate random miscarriages from behaviorally induced miscarriages (those caused by smoking and drinking) results in a contaminated sample. Furthermore, censored child outcomes produce a corrupted sample. Despite these limitations, the bounds demonstrate that delaying the age at first birth for the current population of non-black teenage mothers reduces their first-born child’s well-being.
    Journal of the American Statistical Association 12/2008; 103(484):1334-1344. DOI:10.1198/016214508000000733 · 1.98 Impact Factor
Show more