Mediation and spillover effects in group-randomized trials: a case study of the 4Rs educational intervention

Contamination in Observational Research on Child Maltreatment: A Conceptual and Empirical Review With Implications for Future Research

Contamination is a methodological phenomenon occurring in child maltreatment research when individuals in an established comparison condition have, in reality, been exposed to maltreatment during childhood. The current paper: (1) provides a conceptual and methodological introduction to contamination in child maltreatment research, (2) reviews the empirical literature demonstrating that the presence of contamination biases causal estimates in both prospective and retrospective cohort studies of child maltreatment effects, (3) outlines a dual measurement strategy for how child maltreatment researchers can address contamination, and (4) describes modern statistical methods for generating causal estimates in child maltreatment research after contamination is controlled. Our goal is to introduce the issue of contamination to researchers examining the effects of child maltreatment in an effort to improve the precision and replication of causal estimates that ultimately inform scientific and clinical decision-making as well as public policy.

Effectiveness of a social-emotional learning program on developmental assets and subjective well-being

The present study was done to evaluate the effectiveness of a Social Emotional Learning (SEL) intervention designed based on social marketing on developmental assets and the well-being of female adolescents in Yazd, Iran. This mixed-method quasi-experimental study was conducted in 2018-2019. A total of 190 female students were selected by multi-stage sampling from the female middle and high schools in Yazd, Iran. A SEL intervention designed based on social marketing principles was implemented among the parents and students of the intervention group. The control group did not receive any intervention. Quantitative data were collected in three stages: pre-test, post-test after two months, and follow-up after six months via Developmental Assets Profile and EPOCH measure of wellbeing. A qualitative evaluation was also performed after the intervention. Results of the Repeated-Measures test indicated that the intervention significantly influenced social competence (p-value = .02). However results did not show improvement in the positive identity development of the participant girls. Qualitative findings suggested the effectiveness of the intervention on social competencies and positive identity. Based on the results of the present study, the SEL program might have a significant but small positive effect on the social competencies of the participating adolescents.

ASSESSING TIME-VARYING CAUSAL EFFECT MODERATION IN THE PRESENCE OF CLUSTER-LEVEL TREATMENT EFFECT HETEROGENEITY AND INTERFERENCE

The micro-randomized trial (MRT) is a sequential randomized experimental design to empirically evaluate the effectiveness of mobile health (mHealth) intervention components that may be delivered at hundreds or thousands of decision points. MRTs have motivated a new class of causal estimands, termed "causal excursion effects", for which semiparametric inference can be conducted via a weighted, centered least squares criterion (Boruvka et al., 2018). Existing methods assume between-subject independence and non-interference. Deviations from these assumptions often occur. In this paper, causal excursion effects are revisited under potential cluster-level treatment effect heterogeneity and interference, where the treatment effect of interest may depend on cluster-level moderators. Utility of the proposed methods is shown by analyzing data from a multi-institution cohort of first year medical residents in the United States.

Statistical inference and power analysis for direct and spillover effects in two-stage randomized experiments

Two-stage randomized experiments become an increasingly popular experimental design for causal inference when the outcome of one unit may be affected by the treatment assignments of other units in the same cluster. In this paper, we provide a methodological framework for general tools of statistical inference and power analysis for two-stage randomized experiments. Under the randomization-based framework, we consider the estimation of a new direct effect of interest as well as the average direct and spillover effects studied in the literature. We provide unbiased estimators of these causal quantities and their conservative variance estimators in a general setting. Using these results, we then develop hypothesis testing procedures and derive sample size formulas. We theoretically compare the two-stage randomized design with the completely randomized and cluster randomized designs, which represent two limiting designs. Finally, we conduct simulation studies to evaluate the empirical performance of our sample size formulas. For empirical illustration, the proposed methodology is applied to the randomized evaluation of the Indian National Health Insurance Program. An open-source software package is available for implementing the proposed methodology.

Accounting for Context in Randomized Trials after Assignment

Many preventive trials randomize individuals to intervention condition which is then delivered in a group setting. Other trials randomize higher levels, say organizations, and then use learning collaboratives comprised of multiple organizations to support improved implementation or sustainment. Other trials randomize or expand existing social networks and use key opinion leaders to deliver interventions through these networks. We use the term contextually driven to refer generally to such trials (traditionally referred to as clustering, where groups are formed either pre-randomization or post-randomization - i.e., a cluster-randomized trial), as these groupings or networks provide fixed or time-varying contexts that matter both theoretically and practically in the delivery of interventions. While such contextually driven trials can provide efficient and effective ways to deliver and evaluate prevention programs, they all require analytical procedures that take appropriate account of non-independence, something not always appreciated. Published analyses of many prevention trials have failed to take this into account. We discuss different types of contextually driven designs and then show that even small amounts of non-independence can inflate actual Type I error rates. This inflation leads to rejecting the null hypotheses too often, and erroneously leading us to conclude that there are significant differences between interventions when they do not exist. We describe a procedure to account for non-independence in the important case of a two-arm trial that randomizes units of individuals or organizations in both arms and then provides the active treatment in one arm through groups formed after assignment. We provide sample code in multiple programming languages to guide the analyst, distinguish diverse contextually driven designs, and summarize implications for multiple audiences.

Invited Commentary: Conducting and Emulating Trials to Study Effects of Social Interventions

All else being equal, if we had 1 causal effect we wished to estimate, we would conduct a randomized trial with a protocol that mapped onto that causal question, or we would attempt to emulate that target trial with observational data. However, studying the social determinants of health often means there are not just 1 but several causal contrasts of simultaneous interest and importance, and each of these related but distinct causal questions may have varying degrees of feasibility in conducting trials. With this in mind, we discuss challenges and opportunities that arise when conducting and emulating such trials. We describe designing trials with the simultaneous goals of estimating the intention-to-treat effect, the per-protocol effect, effects of alternative protocols or joint interventions, effects within subgroups, and effects under interference, and we describe ways to make the most of all feasible randomized trials and emulated trials using observational data. Our comments are grounded in the study results of Courtin et al. (Am J Epidemiol. 2022;191(8):1444-1452).

A Guideline for Reporting Mediation Analyses of Randomized Trials and Observational Studies: The AGReMA Statement

Importance

Mediation analyses of randomized trials and observational studies can generate evidence about the mechanisms by which interventions and exposures may influence health outcomes. Publications of mediation analyses are increasing, but the quality of their reporting is suboptimal.

Objective

To develop international, consensus-based guidance for the reporting of mediation analyses of randomized trials and observational studies (A Guideline for Reporting Mediation Analyses; AGReMA).

Design, Setting, and Participants

The AGReMA statement was developed using the Enhancing Quality and Transparency of Health Research (EQUATOR) methodological framework for developing reporting guidelines. The guideline development process included (1) an overview of systematic reviews to assess the need for a reporting guideline; (2) review of systematic reviews of relevant evidence on reporting mediation analyses; (3) conducting a Delphi survey with panel members that included methodologists, statisticians, clinical trialists, epidemiologists, psychologists, applied clinical researchers, clinicians, implementation scientists, evidence synthesis experts, representatives from the EQUATOR Network, and journal editors (n = 19; June-November 2019); (4) having a consensus meeting (n = 15; April 28-29, 2020); and (5) conducting a 4-week external review and pilot test that included methodologists and potential users of AGReMA (n = 21; November 2020).

Results

A previously reported overview of 54 systematic reviews of mediation studies demonstrated the need for a reporting guideline. Thirty-three potential reporting items were identified from 3 systematic reviews of mediation studies. Over 3 rounds, the Delphi panelists ranked the importance of these items, provided 60 qualitative comments for item refinement and prioritization, and suggested new items for consideration. All items were reviewed during a 2-day consensus meeting and participants agreed on a 25-item AGReMA statement for studies in which mediation analyses are the primary focus and a 9-item short-form AGReMA statement for studies in which mediation analyses are a secondary focus. These checklists were externally reviewed and pilot tested by 21 expert methodologists and potential users, which led to minor adjustments and consolidation of the checklists.

Conclusions and Relevance

The AGReMA statement provides recommendations for reporting primary and secondary mediation analyses of randomized trials and observational studies. Improved reporting of studies that use mediation analyses could facilitate peer review and help produce publications that are complete, accurate, transparent, and reproducible.

Causal inference under interference with prognostic scores for dynamic group therapy studies

Group therapy is a common treatment modality for behavioral health conditions. Patients often enter and exit groups on an ongoing basis, leading to dynamic therapy groups. Examining the effect of high versus low session attendance on patient outcomes is a research question of interest. However, there are several challenges to identifying causal effects in this setting, including the lack of randomization, interference among patients, and the interrelatedness of patient participation. Dynamic therapy groups motivate a unique causal inference scenario, as the treatment statuses are completely defined by the patient attendance record for the therapy session, which is also the structure inducing interference. We adopt the Rubin causal model framework to define the causal effect of high versus low session attendance of group therapy at both the individual patient and peer levels. We propose a strategy to identify individual, peer, and total effects of high attendance versus low attendance on patient outcomes by the prognostic score stratification. We examine performance of our approach via simulation and apply it to data from a group cognitive behavioral therapy trial for treating depression among patients in a substance use disorders treatment setting.

Power and Sample Size Determination for Multilevel Mediation in Three-Level Cluster-Randomized Trials

Mediation analyses supply a principal lens to probe the pathways through which a treatment acts upon an outcome because they can dismantle and test the core components of treatments and test how these components function as a coordinated system or theory of action. Experimental evaluation of mediation effects in addition to total effects has become increasingly common but literature has developed only limited guidance on how to plan mediation studies with multi-tiered hierarchical or clustered structures. In this study, we provide methods for computing the power to detect mediation effects in three-level cluster-randomized designs that examine individual- (level one), intermediate- (level two) or cluster-level (level three) mediators. We assess the methods using a simulation and provide examples of a three-level clinic-randomized study (individuals nested within therapists nested within clinics) probing an individual-, intermediate- or cluster-level mediator using the R package PowerUpR and its Shiny application.

Predictive cluster level surrogacy in the presence of interference

Surrogate evaluation is a difficult problem that is made more so by the presence of interference. Our proposed procedure can allow for relatively easy evaluation of surrogates for indirect or spill-over clinical effects at the cluster level. Our definition of surrogacy is based on the causal-association paradigm (Joffe and Greene, 2009. Related causal frameworks for surrogate outcomes. Biometrics65, 530-538), under which surrogates are evaluated by the strength of the association between a causal treatment effect on the clinical outcome and a causal treatment effect on the candidate surrogate. Hudgens and Halloran (2008, Toward causal inference with interference. Journal of the American Statistical Association103, 832-842) introduced estimators that can be used for many of the marginal causal estimands of interest in the presence of interference. We extend these to consider surrogates for not just direct effects, but indirect and total effects at the cluster level. We suggest existing estimators that can be used to evaluate biomarkers under our proposed definition of surrogacy. In our motivating setting of a transmission blocking malaria vaccine, there is expected to be no direct protection to those vaccinated and predictive surrogates are urgently needed. We use a set of simulated data examples based on the proposed Phase IIb/III trial design of transmission blocking malaria vaccine to demonstrate how our definition, proposed criteria and procedure can be used to identify biomarkers as predictive cluster level surrogates in the presence of interference on the clinical outcome.

Evaluating the impact of larviciding with Bti and community education and mobilization as supplementary integrated vector management interventions for malaria control in Kenya and Ethiopia

Background

Malaria prevention in Africa is mainly through the use of long-lasting insecticide treated nets (LLINs). The objective of the study was to assess the effect of supplementing LLINs with either larviciding with Bacillus thuringiensis israelensis (Bti) or community education and mobilization (CEM), or with both interventions in the context of integrated vector management (IVM).

Methods

The study involved a factorial, cluster-randomized, controlled trial conducted in Malindi and Nyabondo sites in Kenya and Tolay site in Ethiopia, to assess the impact of the following four intervention options on mosquitoes and malaria prevalence: LLINs only (arm 1); LLINs and Bti (arm 2); LLINs and CEM (arm 3); and, LLINs combined with Bti and CEM (arm 4). Between January 2013 and December 2015, CDC light traps were used to sample adult mosquitoes during the second, third and fourth quarter of each year in 10 houses in each of 16 villages at each of the three study sites. Larvae were sampled once a fortnight from potential mosquito-breeding habitats using standard plastic dippers. Cross-sectional malaria parasite prevalence surveys were conducted involving a total of 11,846 primary school children during the 3-year period, including 4800 children in Tolay, 3000 in Malindi and 4046 in Nyabondo study sites.

Results

Baseline relative indoor anopheline density was 0.11, 0.05 and 0.02 mosquitoes per house per night in Malindi, Tolay and Nyabondo sites, respectively. Nyabondo had the highest recorded overall average malaria prevalence among school children at 32.4%, followed by Malindi with 5.7% and Tolay 1.7%. There was no significant reduction in adult anopheline density at each of the three sites, which could be attributed to adding of the supplementary interventions to the usage of LLINs. Malaria prevalence was significantly reduced by 50% in Tolay when using LLINs coupled with application of Bti, community education and mobilization. The two other sites did not reveal significant reduction of prevalence as a result of combining LLINs with any of the other supplementary interventions.

Conclusion

Combining LLINs with larviciding with Bti and CEM further reduced malaria infection in a low prevalence setting in Ethiopia, but not at sites with relatively higher prevalence in Kenya. More research is necessary at the selected sites in Kenya to periodically determine the suite of vector control interventions and broader disease management strategies, which when integrated would further reduce adult anopheline populations and malaria prevalence beyond what is achieved with LLINs.

Evaluating spillover of HIV knowledge from study participants to their network members in a stepped-wedge behavioural intervention in Tanzania

OBJECTIVES

We aim to describe the social network members of participants of a behavioural intervention, and examine how the effects of the intervention may spillover among network members.

DESIGN

Secondary analysis of a step-wedge randomised controlled trial.

SETTING

Change agents (CAs) were recruited from waiting rooms of HIV treatment facilities in Dar es Salaam, Tanzania, and their network members (NMs) were recruited directly by CAs.

PARTICIPANTS

We enrolled 662 CAs in an HIV behavioural intervention. They, along with 710 of their NMs, completed baseline and follow-up interviews from 2011 to 2013.

PRIMARY AND SECONDARY OUTCOMES

The primary outcome of this study was change in NMs' HIV knowledge, and the secondary outcome was whether the NM was lost to follow-up.

RESULTS

At baseline, many characteristics were different between NMs and CAs. We found a number of NM characteristics significantly associated with follow-up of NMs, particularly female gender (OR=1.64, 95% CI: 1.02 to 2.63) and HIV knowledge (OR=20.0, 95% CI: 3.70 to 125); only one CA variable was significantly associated with NM follow-up: having a private source of water (OR=2.17, 95% CI: 1.33 to 3.57). The 14.2% increase in NMs' HIV knowledge was largely due to CAs feeling empowered to pass on prior knowledge, rather than transmitting new knowledge to their NMs.

CONCLUSIONS

Characteristics of social network members of persons living with HIV persons living with HIV may play a role in study retention. Additionally, the HIV knowledge of these NMs increased largely as a function of CA participation in the intervention, suggesting that intervening among highly-connected individuals may maximise benefits to the potential population for whom spillover can occur.

TRIAL REGISTRATION NUMBER

Clinical Trial: NCT01693458; Post-results.

Spatial regression and spillover effects in cluster randomized trials with count outcomes

This paper describes methodology for analyzing data from cluster randomized trials with count outcomes, taking indirect effects as well spatial effects into account. Indirect effects are modeled using a novel application of a measure of depth within the intervention arm. Both direct and indirect effects can be estimated accurately even when the proposed model is misspecified. We use spatial regression models with Gaussian random effects, where the individual outcomes have distributions overdispersed with respect to the Poisson, and the corresponding direct and indirect effects have a marginal interpretation. To avoid spatial confounding, we use orthogonal regression, in which random effects represent spatial dependence using a homoscedastic and dimensionally reduced modification of the intrinsic conditional autoregression model. We illustrate the methodology using spatial data from a pair-matched cluster randomized trial against the dengue mosquito vector Aedes aegypti, done in Trujillo, Venezuela.

THE STRATIFIED MICRO-RANDOMIZED TRIAL DESIGN: SAMPLE SIZE CONSIDERATIONS FOR TESTING NESTED CAUSAL EFFECTS OF TIME-VARYING TREATMENTS

Technological advancements in the field of mobile devices and wearable sensors have helped overcome obstacles in the delivery of care, making it possible to deliver behavioral treatments anytime and anywhere. Here, we discuss our work on the design of a mobile health smoking cessation intervention study with the goal of assessing whether reminders, delivered at times of stress, result in a reduction/prevention of stress in the near-term, and whether this effect changes with time in study. Multiple statistical challenges arose in this effort, leading to the development of the stratified micro-randomized trial design. In these designs, each individual is randomized to treatment repeatedly at times determined by predictions of risk. These risk times may be impacted by prior treatment. We describe the statistical challenges and detail how they can be met.

A Recipe for inferference: Start with Causal Inference. Add Interference. Mix Well with R

In causal inference, interference occurs when the treatment of one subject affects the outcome of other subjects. Interference can distort research conclusions about causal effects when not accounted for properly. In the absence of interference, inverse probability weighted (IPW) estimators are commonly used to estimate causal effects from observational data. Recently, IPW estimators have been extended to handle interference. Tchetgen Tchetgen and VanderWeele (2012) proposed IPW methods to estimate direct and indirect (or spillover) effects that allow for interference between individuals within groups. In this paper, we present inferference, an R package that computes these IPW causal effect estimates when interference may be present within groups. We illustrate use of the package with examples from political science and infectious disease.

Review of Recent Methodological Developments in Group-Randomized Trials: Part 2-Analysis

In 2004, Murray et al. reviewed methodological developments in the design and analysis of group-randomized trials (GRTs). We have updated that review with developments in analysis of the past 13 years, with a companion article to focus on developments in design. We discuss developments in the topics of the earlier review (e.g., methods for parallel-arm GRTs, individually randomized group-treatment trials, and missing data) and in new topics, including methods to account for multiple-level clustering and alternative estimation methods (e.g., augmented generalized estimating equations, targeted maximum likelihood, and quadratic inference functions). In addition, we describe developments in analysis of alternative group designs (including stepped-wedge GRTs, network-randomized trials, and pseudocluster randomized trials), which require clustering to be accounted for in their design and analysis.

Assessing Time-Varying Causal Effect Moderation in Mobile Health

In mobile health interventions aimed at behavior change and maintenance, treatments are provided in real time to manage current or impending high risk situations or promote healthy behaviors in near real time. Currently there is great scientific interest in developing data analysis approaches to guide the development of mobile interventions. In particular data from mobile health studies might be used to examine effect moderators-individual characteristics, time-varying context or past treatment response that moderate the effect of current treatment on a subsequent response. This paper introduces a formal definition for moderated effects in terms of potential outcomes, a definition that is particularly suited to mobile interventions, where treatment occasions are numerous, individuals are not always available for treatment, and potential moderators might be influenced by past treatment. Methods for estimating moderated effects are developed and compared. The proposed approach is illustrated using BASICS-Mobile, a smartphone-based intervention designed to curb heavy drinking and smoking among college students.

Identification and Estimation of Causal Mechanisms in Clustered Encouragement Designs: Disentangling Bed Nets using Bayesian Principal Stratification

Exploration of causal mechanisms is often important for researchers and policymakers to understand how an intervention works and how it can be improved. This task can be crucial in clustered encouragement designs (CED). Encouragement design studies arise frequently when the treatment cannot be enforced because of ethical or practical constrains and an encouragement intervention (information campaigns, incentives, etc) is conceived with the purpose of increasing the uptake of the treatment of interest. By design, encouragements always entail the complication of non-compliance. Encouragements can also give rise to a variety of mechanisms, particularly when encouragement is assigned at cluster level. Social interactions among units within the same cluster can result in spillover effects. Disentangling the effect of encouragement through spillover effects from that through the enhancement of the treatment would give better insight into the intervention and it could be compelling for planning the scaling-up phase of the program. Building on previous works on CEDs and non-compliance, we use the principal stratification framework to define stratum-specific causal effects, that is, effects for specific latent subpopulations, defined by the joint potential compliance statuses under both encouragement conditions. We show how the latter stratum-specific causal effects are related to the decomposition commonly used in the literature and provide flexible homogeneity assumptions under which an extrapolation across principal strata allows one to disentangle the effects. Estimation of causal estimands can be performed with Bayesian inferential methods using hierarchical models to account for clustering. We illustrate the proposed methodology by analyzing a cluster randomized experiment implemented in Zambia and designed to evaluate the impact on malaria prevalence of an agricultural loan program intended to increase the bed net coverage. Farmer households assigned to the program could take advantage of a deferred payment and a discount in the purchase of new bed nets. Our analysis shows a lack of evidence of an effect of the offering of the program to a cluster of households through spillover effects, that is through a greater bed net coverage in the neighborhood.

Measuring What Works: An Impact Evaluation of Women's Groups on Maternal Health Uptake in Rural Nepal

BACKGROUND

There is a need for studies evaluating maternal health interventions in low-income countries. This paper evaluates one such intervention designed to promote maternal health among rural women in Nepal.

METHODS AND RESULTS

This was a five-year controlled, non-randomised, repeated cross-sectional study (2007, 2010, 2012) of a participatory community-based maternal health promotion intervention focusing on women's groups to improve maternal health services uptake. In total 1,236 women of childbearing age, who had their last child ≤ two years ago, were interviewed. Difference-in-Difference estimation assessed the effects of the intervention on selected outcome variables while controlling for a constructed wealth index and women's characteristics. In the first three years (from 2007 to the 2010), the intervention increased women's likelihood of attending for antenatal care at least once during pregnancy by seven times [OR = 7.0, 95%CI (2.3; 21.4)], of taking iron and folic acid by three times [OR = 3.0, 95%CI (1.2; 7.8)], and of seeking four or more antenatal care visits of two times, although not significantly [OR = 2.2, 95%CI (1.0; 4.7)]. Over five years, women were more likely to seek antenatal care at least once [OR = 3.0, 95%CI (1.5; 5.2)], to take iron/folic acid [OR = 1.9, [95% CI (1.1; 3.2)], and to attend postnatal care [OR = 1.5, [95% CI (1.1; 2.2)]. No improvement was found on attending antenatal care in the first trimester, birthing at an institution or with a skilled birth attendant.

CONCLUSION

Community-based health promotion has a much stronger effect on the uptake of antenatal care and less on delivery care. Other factors not easily resolved through health promotion interventions may influence these outcomes, such as costs or geographical constraints. The evaluation has implications for policy and practice in public health, especially maternal health promotion.

Bayesian Causal Mediation Analysis for Group Randomized Designs with Homogeneous and Heterogeneous Effects: Simulation and Case Study

A fully Bayesian approach to causal mediation analysis for group-randomized designs is presented. A unique contribution of this article is the combination of Bayesian inferential methods with G-computation to address the problem of heterogeneous treatment or mediator effects. A detailed simulation study shows that this approach has excellent frequentist properties, particularly in the case of small sample sizes with accurate informative priors. The simulation study also demonstrates that the proposed approach can take into account heterogeneous treatment or mediator effects without bias. A case study using data from a school-based randomized intervention designed to increase parent social capital leading to improved behavioral and academic outcomes in children is offered to illustrate the Bayesian approach to causal mediation in group-randomized designs.

Interference and Sensitivity Analysis

Causal inference with interference is a rapidly growing area. The literature has begun to relax the "no-interference" assumption that the treatment received by one individual does not affect the outcomes of other individuals. In this paper we briefly review the literature on causal inference in the presence of interference when treatments have been randomized. We then consider settings in which causal effects in the presence of interference are not identified, either because randomization alone does not suffice for identification, or because treatment is not randomized and there may be unmeasured confounders of the treatment-outcome relationship. We develop sensitivity analysis techniques for these settings. We describe several sensitivity analysis techniques for the infectiousness effect which, in a vaccine trial, captures the effect of the vaccine of one person on protecting a second person from infection even if the first is infected. We also develop two sensitivity analysis techniques for causal effects in the presence of unmeasured confounding which generalize analogous techniques when interference is absent. These two techniques for unmeasured confounding are compared and contrasted.

Mediation analysis with multiple versions of the mediator

The causal inference literature has provided definitions of direct and indirect effects based on counterfactuals that generalize the approach found in the social science literature. However, these definitions presuppose well-defined hypothetical interventions on the mediator. In many settings, there may be multiple ways to fix the mediator to a particular value, and these various hypothetical interventions may have very different implications for the outcome of interest. In this paper, we consider mediation analysis when multiple versions of the mediator are present. Specifically, we consider the problem of attempting to decompose a total effect of an exposure on an outcome into the portion through the intermediate and the portion through other pathways. We consider the setting in which there are multiple versions of the mediator but the investigator has access only to data on the particular measurement, not information on which version of the mediator may have brought that value about. We show that the quantity that is estimated as a natural indirect effect using only the available data does indeed have an interpretation as a particular type of mediated effect; however, the quantity estimated as a natural direct effect, in fact, captures both a true direct effect and an effect of the exposure on the outcome mediated through the effect of the version of the mediator that is not captured by the mediator measurement. The results are illustrated using 2 examples from the literature, one in which the versions of the mediator are unknown and another in which the mediator itself has been dichotomized.