Efficiency and robustness of causal effect estimators when noncompliance is measured with error.
ABSTRACT: Estimating causal effects from randomized controlled trials is often complicated due to participant noncompliance to randomized treatment. Although there are a variety of methods to estimate causal effects in the presence of noncompliance, they generally make the assumption that noncompliance is measured without error. This is frequently an untenable assumption, particularly when noncompliance is based on participant self-report. To overcome this issue, we treat compliance as an unobserved variable and show how to estimate the probability of compliance given a biomarker of treatment and the other observed data. We present inverse probability weighted estimators, regression-based estimators, and a doubly-robust augmented estimator that rely on the estimated probability of compliance rather than an indicator of compliance. We investigate the finite-sample properties of the estimators and their efficiency and robustness under correctly specified or misspecified models, and we apply the estimators to a recently completed trial of very low nicotine content cigarettes.
Project description:Noncompliance or non-adherence to randomized treatment is a common challenge when interpreting data from randomized clinical trials. The effect of an intervention if all participants were forced to comply with the assigned treatment (i.e., the causal effect) is often of primary scientific interest. For example, in trials of very low nicotine content (VLNC) cigarettes, policymakers are interested in their effect on smoking behavior if their use were to be compelled by regulation. A variety of statistical methods to estimate the causal effect of an intervention have been proposed, but these methods, including inverse probability of compliance weighted (IPCW) estimators, assume that participants' compliance statuses are reported without error. This is an untenable assumption when compliance is based on self-report. Biomarkers (e.g., nicotine levels in the urine) may provide more reliable indicators of compliance but cannot perfectly discriminate between compliers and non-compliers. However, by modeling the distribution of the biomarker as a mixture distribution and writing the probability of compliance as a function of the mixture components, we show how the probability of compliance can be directly estimated from the data even when compliance status is unknown. To estimate the causal effect, we develop a new approach which re-weights participants by the product of their probability of compliance given the observed data and the inverse probability of compliance given confounders. We show that our proposed estimator is consistent and asymptotically normal and show that in some situations the proposed approach is more efficient than standard IPCW estimators. We demonstrate via simulation that the proposed estimator achieves smaller bias and greater efficiency than ad hoc approaches to estimating the causal effect when compliance is measured with error. We apply our method to data from a recently completed randomized trial of VLNC cigarettes.
Project description:Cluster randomized trials (CRTs) have been widely used in field experiments treating a cluster of individuals as the unit of randomization. This study focused particularly on situations where CRTs are accompanied by a common complication, namely, treatment noncompliance or, more generally, intervention nonadherence. In CRTs, compliance may be related not only to individual characteristics but also to the environment of clusters individuals belong to. Therefore, analyses ignoring the connection between compliance and clustering may not provide valid results. Although randomized field experiments often suffer from both noncompliance and clustering of the data, these features have been studied as separate rather than concurrent problems. On the basis of Monte Carlo simulations, this study demonstrated how clustering and noncompliance may affect statistical inferences and how these two complications can be accounted for simultaneously. In particular, the effect of the intervention on individuals who not only were assigned to active intervention but also abided by this intervention assignment (complier average causal effect) was the focus. For estimation of intervention effects considering noncompliance and data clustering, an ML-EM estimation method was employed.
Project description:Instrumental variables (IV) estimators are well established to correct for measurement error on exposure in a broad range of fields. In a distinct prominent stream of research IV's are becoming increasingly popular for estimating causal effects of exposure on outcome since they allow for unmeasured confounders which are hard to avoid. Because many causal questions emerge from data which suffer severe measurement error problems, we combine both IV approaches in this article to correct IV-based causal effect estimators in linear (structural mean) models for possibly systematic measurement error on the exposure. The estimators rely on the presence of a baseline measurement which is associated with the observed exposure and known not to modify the target effect. Simulation studies and the analysis of a small blood pressure reduction trial (n = 105) with treatment noncompliance confirm the adequate performance of our estimators in finite samples. Our results also demonstrate that incorporating limited prior knowledge about a weakly identified parameter (such as the error mean) in a frequentist analysis can yield substantial improvements.
Project description:In this article, we first study parameter identifiability in randomized clinical trials with noncompliance and missing outcomes. We show that under certain conditions the parameters of interest are identifiable even under different types of completely nonignorable missing data: that is, the missing mechanism depends on the outcome. We then derive their maximum likelihood and moment estimators and evaluate their finite-sample properties in simulation studies in terms of bias, efficiency, and robustness. Our sensitivity analysis shows that the assumed nonignorable missing-data model has an important impact on the estimated complier average causal effect (CACE) parameter. Our new method provides some new and useful alternative nonignorable missing-data models over the existing latent ignorable model, which guarantees parameter identifiability, for estimating the CACE in a randomized clinical trial with noncompliance and missing data.
Project description:<h4>Background</h4>Understanding contraception from the perspective of the user may help to improve compliance. The aim of this project was to determine the factors that influence the noncompliance in young women that use combined hormonal contraceptives (pill, patch or vaginal ring).<h4>Methods</h4>A nationwide cross-sectional multicenter epidemiology study. Physicians [obstetricians/gynecologists]) recorded socio-demographic, clinical and current contraception data of 8,762 women. Women completed a self-administered questionnaire on compliance. After the assessment of self-administrated questionnaire, the physicians reported on their recommendations on the possibility of changing the contraceptive.<h4>Results</h4>Fifty-two percent of women were noncompliant, mainly because of simple forgetfulness (pill, 74.9%; patch, 47.8%; vaginal ring, 69.1%). The percentage of noncompliant women was lower in vaginal ring users (26.6%) than in patch users (42.4%) or pill users (65.1%) (p?<?0.0001). The most common course of action after noncompliance was to take/use the contraceptive as soon as possible. In the multiple logistic regression analysis, the use of the pill increased the probability of noncompliance compared with the patch and the vaginal ring (odds ratio [IC95%]: 2.53 (2.13-3.02) and 4.17 (3.68-4.73, respectively), and using the patch compared with the vaginal ring (1.65 (1.36-1.99)). Others factors associated with noncompliance were: high treatment duration, low degree of information on the contraceptive method, understanding of instructions on the contraceptive method, indifference to becoming pregnant, lack of partner support, not participation in selecting the method, not having a routine for taking treatment and difficulties remembering use the contraceptive method. Switching contraceptive method was proposed by the physicians to 43.2% of women (51.8% of pill users, 58.2% of patch users and 19.4% of vaginal ring users).<h4>Conclusions</h4>More than 50% of combined hormonal contraceptive users did not comply with the treatment regimen. The percentage of noncompliant women was lower between vaginal ring users. Understanding user's reasons for noncompliance by the clinician and encouraging a collaborative approach can go a long way to improving compliance.
Project description:The reduction of the nicotine content of cigarettes to nonaddicting levels is a potential federal regulatory intervention to reduce the prevalence of cigarette smoking and related disease. Many clinical trials on the effects and safety of nicotine reduction are ongoing. An important methodologic concern is noncompliance with reduced nicotine content cigarettes in the context of freely available conventional cigarettes. We propose two approaches using biomarkers to estimate noncompliance in smokers of very low nicotine content (VLNC) cigarettes in a clinical trial.Data from 50 subjects in a study of gradual nicotine reduction were analyzed. Using plasma cotinine concentrations measured at baseline and while smoking VLNC cigarettes, we compared within-subject ratios of plasma cotinine comparing usual brand to VLNC in relation to nicotine content of these cigarettes. In another approach, we used nicotine pharmacokinetic data to estimate absolute plasma cotinine/cigarettes per day (CPD) threshold values for compliance based on the nicotine content of VLNC.The two approaches showed concordance, indicating at least 60% noncompliance with smoking VLNC. In a sensitivity analysis assuming extreme compensation and extreme values for nicotine metabolic parameters, noncompliance was still at least 40%, much higher than self-reported noncompliance.Biomarker analysis demonstrates a high degree of noncompliance with smoking VLNC cigarettes, indicating that smokers are supplementing these with conventional cigarettes.We propose a practical approach to assessing compliance with smoking VLNC in clinical trials of nicotine reduction.
Project description:Premature discontinuation and other forms of noncompliance with treatment assignment can complicate causal inference of treatment effects in randomized trials. The intent-to-treat analysis gives unbiased estimates for causal effects of treatment assignment on outcome, but may understate potential benefit or harm of actual treatment. The corresponding upper confidence limit can also be underestimated.To compare estimates of the hazard ratio and upper bound of the two-sided 95% confidence interval from causal inference methods that account for noncompliance with those from the intent-to-treat analysis.We used simulations with parameters chosen to reflect cardiovascular safety trials of diabetes drugs, with a focus on upper bound estimates relative to 1.3, based on regulatory guidelines. A total of 1000 simulations were run under each parameter combination for a hypothetical trial of 10,000 total subjects randomly assigned to active treatment or control at 1:1 ratio. Noncompliance was considered in the form of treatment discontinuation and cross-over at specified proportions, with an assumed true hazard ratio of 0.9, 1, and 1.3, respectively. Various levels of risk associated with being a non-complier (independent of treatment status) were evaluated. Hazard ratio and upper bound estimates from causal survival analysis and intent-to-treat were obtained from each simulation and summarized under each parameter setting.Causal analysis estimated the true hazard ratio with little bias in almost all settings examined. Intent-to-treat was unbiased only when the true hazard ratio?=?1; otherwise it underestimated both benefit and harm. When upper bound estimates from intent-to-treat were ?1.3, corresponding estimates from causal analysis were also ?1.3 in almost 100% of the simulations, regardless of the true hazard ratio. When upper bound estimates from intent-to-treat were <1.3 and the true hazard ratio?=?1, corresponding upper bound estimates from causal analysis were ?1.3 in up to 66% of the simulations under some settings.Simulations cannot cover all scenarios for noncompliance in real randomized trials.Causal survival analysis was superior to intent-to-treat in estimating the true hazard ratio with respect to bias in the presence of noncompliance. However, its large variance should be considered for safety upper bound exclusion especially when the true hazard ratio?=?1. Our simulations provided a broad reference for practical considerations of bias-variance trade-off in dealing with noncompliance in cardiovascular safety trials of diabetes drugs. Further research is warranted for the development and application of causal inference methods in the evaluation of safety upper bounds.
Project description:Natural resource rules exist to control resources and the people that interact with them. These rules often fail because people do not comply with them. Decisions to comply with natural resource rules often are based on attitudes about legitimacy of rules and the perceived risks of breaking rules. Trust in agencies promulgating rules in part may determine perceptions of legitimacy of the rule, and in turn depends on individuals' trust in different agency actors. The purpose of this research is to explore the relationship between fishing rule noncompliance and trust in scientists, a key group within management agencies. We interviewed 41 individuals in one rural fishing community in the Brazilian Pantanal from April to August, 2016, to assess (1) noncompliance rates, (2) noncompliance-related attitudes, and (3) the relationship between trust in scientists and noncompliance decisions in the region. We found that among study participants, noncompliance was common and overt. Trust in scientists performing research in the region was the best predictor of noncompliance rate with a fishing rule (nonparametric rank correlation ? = -0.717; Probit model pseudo-R2 = 0.241). Baseline data from this research may help inform future interventions to minimize IUU fishing and protect the Pantanal fishery. Although our results are specific to one community in the Pantanal, trust in scientists is potentially an important factor for compliance decisions in similar situations around the world. These results build not only on compliance theory but also speak to the important role that many scientists play in rural areas where they conduct their research.
Project description:Randomization can be used as an instrumental variable (IV) to account for unmeasured confounding when seeking to assess the impact of noncompliance with treatment allocation in a randomized trial. We present and compare different methods to calculate the treatment effect on a binary outcome as a rate ratio in a randomized surgical trial.The effectiveness of peeling versus not peeling the internal limiting membrane of the retina as part of the surgery for a full thickness macular hole. We compared the IV-based estimates (nonparametric causal bound and two-stage residual inclusion approach [2SRI]) with standard treatment effect measures (intention to treat, per protocol and treatment received [TR]). Compliance was defined in two ways (initial and up to the time point of interest). Poisson regression was used for the model-based approaches with robust standard errors to calculate the risk ratio (RR) with 95% confidence intervals.Results were similar for 1-month macular hole status across methods. For 3- and 6-month macular hole status, nonparametric causal bounds provided a narrower range of uncertainty than other methods, though still had substantial imprecision. For 3-month macular hole status, the TR estimate was substantially different from the other point estimates.Nonparametric causal bound approaches are a useful addition to an IV estimation approach, which tend to have large levels of uncertainty. Methods which allow RRs to be calculated when addressing noncompliance in randomized trials exist and may be superior to standard estimates. Further research is needed to explore the properties of different IV methods in a broad range of randomized controlled trial scenarios.
Project description:Patient noncompliance complicates the analysis of many randomized trials seeking to evaluate the effect of surgical intervention as compared with a nonsurgical treatment. If selection for treatment depends on intermediate patient characteristics or outcomes, then 'as-treated' analyses may be biased for the estimation of causal effects. Therefore, the selection mechanism for treatment and/or compliance should be carefully considered when conducting analysis of surgical trials. We compare the performance of alternative methods when endogenous processes lead to patient crossover. We adopt an underlying longitudinal structural mixed model that is a natural example of a structural nested model. Likelihood-based methods are not typically used in this context; however, we show that standard linear mixed models will be valid under selection mechanisms that depend only on past covariate and outcome history. If there are underlying patient characteristics that influence selection, then likelihood methods can be extended via maximization of the joint likelihood of exposure and outcomes. Semi-parametric causal estimation methods such as marginal structural models, g-estimation, and instrumental variable approaches can also be valid, and we both review and evaluate their implementation in this setting. The assumptions required for valid estimation vary across approaches; thus, the choice of methods for analysis should be driven by which outcome and selection assumptions are plausible.