Sensitivity analyses for parametric causal mediation effect estimation

Causal mediation for uncausally related mediators in the context of survival analysis

Objective

The study of the potential intermediate effect of several variables on the association between an exposure and a time-to-event outcome is a question of interest in epidemiologic research. However, to our knowledge, no tools have been developed for the evaluation of multiple correlated mediators in a survival setting.

Methods

In this work, we extended the multimediate algorithm, which conducts mediation analysis in the context of multiple uncausally correlated mediators, to a time-to-event setting using the semiparametric additive hazards model. We theoretically demonstrated that, under certain assumptions, indirect, direct and total effects can be calculated using the counterfactual framework with collapsible survival models. We also adapted the algorithm to accommodate exposure-mediator interactions.

Results and conclusions

Using simulations, we demonstrated that our algorithm performs better than the product of coefficients method, even for uncorrelated mediators. The additive hazards model quantifies the effects as rate differences, which constitute a measure of impact, with applications that can be highly informative for public health. Our algorithm can be found in the R package multimediate, which is available in Github.

Causal mediation and sensitivity analysis for mixed-scale data

The goal of causal mediation analysis, often described within the potential outcomes framework, is to decompose the effect of an exposure on an outcome of interest along different causal pathways. Using the assumption of sequential ignorability to attain non-parametric identification, Imai et al. (2010) proposed a flexible approach to measuring mediation effects, focusing on parametric and semiparametric normal/Bernoulli models for the outcome and mediator. Less attention has been paid to the case where the outcome and/or mediator model are mixed-scale, ordinal, or otherwise fall outside the normal/Bernoulli setting. We develop a simple, but flexible, parametric modeling framework to accommodate the common situation where the responses are mixed continuous and binary, and, apply it to a zero-one inflated beta model for the outcome and mediator. Applying our proposed methods to the publicly-available JOBS II dataset, we (i) argue for the need for non-normal models, (ii) show how to estimate both average and quantile mediation effects for boundary-censored data, and (iii) show how to conduct a meaningful sensitivity analysis by introducing unidentified, scientifically meaningful, sensitivity parameters.

The impact of omitting confounders in parallel process latent growth curve mediation models: Three sensitivity analysis approaches

Parallel process latent growth curve mediation models (PP-LGCMMs) are frequently used to longitudinally investigate the mediation effects of treatment on the level and change of outcome through the level and change of mediator. An important but often violated assumption in empirical PP-LGCMM analysis is the absence of omitted confounders of the relationships among treatment, mediator, and outcome. In this study, we analytically examined how omitting pretreatment confounders impacts the inference of mediation from the PP-LGCMM. Using the analytical results, we developed three sensitivity analysis approaches for the PP-LGCMM, including the frequentist, Bayesian, and Monte Carlo approaches. The three approaches help investigate different questions regarding the robustness of mediation results from the PP-LGCMM, and handle the uncertainty in the sensitivity parameters differently. Applications of the three sensitivity analyses are illustrated using a real-data example. A user-friendly Shiny web application is developed to conduct the sensitivity analyses.

Relationships between enriching early life experiences and cognitive function later in life are mediated by educational attainment

The study of how engagement in enriching cognitive, physical and social activities in childhood impacts cognitive function decades later will advance our understanding of how modifiable lifestyle activities promote cognition across the lifespan. 88 healthy older adults (aged 60-80 years) returned a retrospective questionnaire regarding their participation in seven lifestyle activities (musical instrument playing, language learning, sport participation, art/dance lessons, scouting, volunteering, family vacations) before age 13 years. After controlling for current age, educational attainment, socioeconomic status of the mother and current engagement in lifestyle activities, a greater number of activities were significantly associated with better vocabulary abilities, episodic memory and fluid intelligence. The relationships with vocabulary and fluid intelligence were mediated by educational attainment. We postulate that engagement in a higher number of enriching early life activities is a reflection of both one's sociocontextual environment and engagement with that environment. This engagement leads to attributes relevant for educational aspirations/attainment, ultimately contributing to factors that have a lifespan impact on cognitive function.

A Review of High-Dimensional Mediation Analyses in DNA Methylation Studies

DNA methylation alterations have been widely studied as mediators of environmentally induced disease risks. With new advances in technique, epigenome-wide DNA methylation data (EWAS) have become the new standard for epigenetic studies in human populations. However, to date most epigenetic studies of mediation effects only involve selected (gene-specific) candidate methylation markers. There is an urgent need for appropriate analytical methods for EWAS mediation analysis. In this chapter, we provide an overview of recent advances on high-dimensional mediation analysis, with application to two DNA methylation data.

Sensitivity Analysis in Nonrandomized Longitudinal Mediation Analysis

Mediation analysis relies on an untestable assumption of the no omitted confounders, which posits that an omitted variable that confounds the relationships between the antecedent, mediator, and outcome variables cannot exist. One common model in alcohol addiction studies is a nonrandomized latent growth curve mediation model (LGCMM), where the antecedent variable is not randomized, the two covarying mediators are latent intercept and slope modeling longitudinal effect of the repeated measures mediator, and an outcome variable that measures alcohol use. An important gap in the literature is lack of sensitivity analysis techniques to assess the effect of the violation of the no omitted confounder assumption in a nonrandomized LGCMM. We extend a sensitivity analysis technique, termed correlated augmented mediation sensitivity analysis (CAMSA), to a nonrandomized LGCMM. We address several unresolved issues in conducting CAMSA for the nonrandomized LGCMM and present: (a) analytical results showing how confounder correlations model a confounding bias, (b) algorithms to address admissible values for confounder correlations, (c) accessible R code within an SEM framework to conduct our proposed sensitivity analysis, and (d) an empirical example. We conclude that conducting sensitivity analysis to ascertain robustness of the mediation analysis is critical.

Acute exercise effects on inhibitory control and the pupillary response in young adults

Previous research has established an impact of acute exercise on cognitive performance, which has inspired investigations into neurobiological mechanisms that may underlie the observed benefits. Pupillary responses have been posited to reflect activation of such underlying neurobiological mechanisms. The current study recruited healthy young adults to investigate the effects of a single bout of moderate-to-vigorous intensity aerobic exercise on subsequent performance and pupillary responses during an inhibitory control task. Results showed that an acute bout of exercise was related to shorter reaction times and increased tonic pupil dilation during an inhibitory control task. Although pupillary responses did not mediate the acute exercise effect on inhibitory control, higher cardiorespiratory fitness was associated with greater phasic pupil dilation following exercise relative to seated rest. The current study supported the plausibility of the pupillary response as a marker of LC-NE system activation that is sensitive to acute exercise. Whether pupillary responses could account for transient benefits of acute exercise on brain and cognition remains unclear.

Insights into the Cross-world Independence Assumption of Causal Mediation Analysis

Causal mediation analysis is a useful tool for epidemiologic research, but it has been criticized for relying on a "cross-world" independence assumption that counterfactual outcome and mediator values are independent even in causal worlds where the exposure assignments for the outcome and mediator differ. This assumption is empirically difficult to verify and problematic to justify based on background knowledge. In the present article, we aim to assist the applied researcher in understanding this assumption. Synthesizing what is known about the cross-world independence assumption, we discuss the relationship between assumptions for causal mediation analyses, causal models, and nonparametric identification of natural direct and indirect effects. In particular, we give a practical example of an applied setting where the cross-world independence assumption is violated even without any post-treatment confounding. Further, we review possible alternatives to the cross-world independence assumption, including the use of bounds that avoid the assumption altogether. Finally, we carry out a numeric study in which the cross-world independence assumption is violated to assess the ensuing bias in estimating natural direct and indirect effects. We conclude with recommendations for carrying out causal mediation analyses.

Latent class mediator for multiple indicators of mediation

This paper demonstrates the utility of latent classes in evaluating the effect of an intervention on an outcome through multiple indicators of mediation. These indicators are observed intermediate variables that identify an underlying latent class mediator, with each class representing a different mediating pathway. The use of a latent class mediator allows us to avoid modeling the complex interactions between the multiple indicators and ensures the decomposition of the total mediating effects into additive effects from individual mediating pathways, a desirable feature for evaluating multiple indicators of mediation. This method is suitable when the goal is to estimate the total mediating effects that can be decomposed into the additive effects of distinct mediating pathways. Each indicator may be involved in multiple mediation pathways and at the same time multiple indicators may contribute to a single mediating pathway. The relative importance of each pathway may vary across subjects. We applied this method to the analysis of the first 6 months of data from a 2-year clustered randomized trial for adults in their first episode of schizophrenia. Four indicators of mediation are considered: individual resiliency training; family psychoeducation; supported education and employment; and a structural assessment for medication. The improvement in symptoms was found to be mediated by the latent class mediator derived from these four service indicators. Simulation studies were conducted to assess the performance of the proposed model and showed that the simultaneous estimation through the maximum likelihood yielded little bias when the entropy of the indicators was high.

Statistical methods for mediation analysis in the era of high-throughput genomics: Current successes and future challenges

Mediation analysis investigates the intermediate mechanism through which an exposure exerts its influence on the outcome of interest. Mediation analysis is becoming increasingly popular in high-throughput genomics studies where a common goal is to identify molecular-level traits, such as gene expression or methylation, which actively mediate the genetic or environmental effects on the outcome. Mediation analysis in genomics studies is particularly challenging, however, thanks to the large number of potential mediators measured in these studies as well as the composite null nature of the mediation effect hypothesis. Indeed, while the standard univariate and multivariate mediation methods have been well-established for analyzing one or multiple mediators, they are not well-suited for genomics studies with a large number of mediators and often yield conservative p-values and limited power. Consequently, over the past few years many new high-dimensional mediation methods have been developed for analyzing the large number of potential mediators collected in high-throughput genomics studies. In this work, we present a thorough review of these important recent methodological advances in high-dimensional mediation analysis. Specifically, we describe in detail more than ten high-dimensional mediation methods, focusing on their motivations, basic modeling ideas, specific modeling assumptions, practical successes, methodological limitations, as well as future directions. We hope our review will serve as a useful guidance for statisticians and computational biologists who develop methods of high-dimensional mediation analysis as well as for analysts who apply mediation methods to high-throughput genomics studies.

Socioeconomic status and survival after stroke - using mediation and sensitivity analyses to assess the effect of stroke severity and unmeasured confounding

Background

Although it has been established that low socioeconomic status is linked to increased risk of death after stroke, the mechanisms behind this link are still unclear. In this study we aim to shed light on the relationship between income level and survival after stroke by investigating the extent to which differences in stroke severity account for differences in survival.

Methods

The study was based on patients registered in Riksstroke (the Swedish stroke register) with first time ischemic stroke (n = 51,159) or intracerebral hemorrhage (n = 6777) in 2009–2012. We used causal mediation analysis to decompose the effect of low income on 3-month case fatality into a direct effect and an indirect effect due to stroke severity. Since causal mediation analysis relies on strong assumptions regarding residual confounding of the relationships involved, recently developed methods for sensitivity analysis were used to assess the robustness of the results to unobserved confounding.

Results

After adjustment for observed confounders, patients in the lowest income tertile had a 3.2% (95% CI: 0.9–5.4%) increased absolute risk of 3-month case fatality after intracerebral hemorrhage compared to patients in the two highest tertiles. The corresponding increase for case fatality after ischemic stroke was 1% (0.4–1.5%). The indirect effect of low income, mediated by stroke severity, was 1.8% (0.7–2.9%) for intracerebral hemorrhage and 0.4% (0.2–0.6%) for ischemic stroke. Unobserved confounders affecting the risk of low income, more severe stroke and case fatality in the same directions could explain the indirect effect, but additional adjustment to observed confounders did not alter the conclusions.

Conclusions

This study provides evidence that as much as half of income-related inequalities in stroke case fatality is mediated through differences in stroke severity. Targeting stroke severity could therefore lead to a substantial reduction in inequalities and should be prioritized. Sensitivity analysis suggests that additional adjustment for a confounder of greater impact than age would be required to considerably alter our conclusions.

Continuous-time causal mediation analysis

While causal mediation analysis has seen considerable recent development for a single measured mediator (M) and final outcome (Y), less attention has been given to repeatedly measured M and Y. Previous methods have typically involved discrete-time models that limit inference to the particular measurement times used and do not recognize the continuous nature of the mediation process over time. To overcome such limitations, we present a new continuous-time approach to causal mediation analysis that uses a differential equations model in a potential outcomes framework to describe the causal relationships among model variables over time. A connection between the differential equation models and standard repeated measures models is made to provide convenient model formulation and fitting. A continuous-time extension of the sequential ignorability assumption allows for identifiable natural direct and indirect effects as functions of time, with estimation based on a two-step approach to model fitting in conjunction with a continuous-time mediation formula. Novel features include a measure of an overall mediation effect based on the "area between the curves," and an approach for predicting the effects of new interventions. Simulation studies show good properties of estimators and the new methodology is applied to data from a cohort study to investigate sugary drink consumption as a mediator of the effect of socioeconomic status on dental caries in children.

Maximum Likelihood Analysis of Linear Mediation Models with Treatment-Mediator Interaction

This research concerns a mediation model, where the mediator model is linear and the outcome model is also linear but with a treatment-mediator interaction term and a residual correlated with the residual of the mediator model. Assuming the treatment is randomly assigned, parameters in this mediation model are shown to be partially identifiable. Under the normality assumption on the residual of the mediator and the residual of the outcome, explicit full-information maximum likelihood estimates of model parameters are introduced given the correlation between the residual for the mediator and the residual for the outcome. A consistent variance matrix of these estimates is derived. Currently, the coefficients of this mediation model are estimated using the iterative feasible generalized least squares (IFGLS) method that is originally developed for seemingly unrelated regressions (SURs). We argue that this mediation model is not a system of SURs. While the IFGLS estimates are consistent, their variance matrix is not. Theoretical comparisons of the FIMLE variance matrix and the IFGLS variance matrix are conducted. Our results are demonstrated by simulation studies and an empirical study. The FIMLE method has been implemented in a freely available R package iMediate.

Generalized causal mediation and path analysis: Extensions and practical considerations

Causal mediation analysis seeks to decompose the effect of a treatment or exposure among multiple possible paths and provide casually interpretable path-specific effect estimates. Recent advances have extended causal mediation analysis to situations with a sequence of mediators or multiple contemporaneous mediators. However, available methods still have limitations, and computational and other challenges remain. The present paper provides an extended causal mediation and path analysis methodology. The new method, implemented in the new R package, gmediation (described in a companion paper), accommodates both a sequence (two stages) of mediators and multiple mediators at each stage, and allows for multiple types of outcomes following generalized linear models. The methodology can also handle unsaturated models and clustered data. Addressing other practical issues, we provide new guidelines for the choice of a decomposition, and for the choice of a reference group multiplier for the reduction of Monte Carlo error in mediation formula computations. The new method is applied to data from a cohort study to illuminate the contribution of alternative biological and behavioral paths in the effect of socioeconomic status on dental caries in adolescence.

Sensitivity analysis for mistakenly adjusting for mediators in estimating total effect in observational studies

OBJECTIVES

In observational studies, epidemiologists often attempt to estimate the total effect of an exposure on an outcome of interest. However, when the underlying diagram is unknown and limited knowledge is available, dissecting bias performances is essential to estimating the total effect of an exposure on an outcome when mistakenly adjusting for mediators under logistic regression. Through simulation, we focused on six causal diagrams concerning different roles of mediators. Sensitivity analysis was conducted to assess the bias performances of varying across exposure-mediator effects and mediator-outcome effects when adjusting for the mediator.

SETTING

Based on the causal relationships in the real world, we compared the biases of varying across the effects of exposure-mediator with those of varying across the effects of mediator-outcome when adjusting for the mediator. The magnitude of the bias was defined by the difference between the estimated effect (using logistic regression) and the total effect of the exposure on the outcome.

RESULTS

In four scenarios (a single mediator, two series mediators, two independent parallel mediators or two correlated parallel mediators), the biases of varying across the effects of exposure-mediator were greater than those of varying across the effects of mediator-outcome when adjusting for the mediator. In contrast, in two other scenarios (a single mediator or two independent parallel mediators in the presence of unobserved confounders), the biases of varying across the effects of exposure-mediator were less than those of varying across the effects of mediator-outcome when adjusting for the mediator.

CONCLUSIONS

The biases were more sensitive to the variation of effects of exposure-mediator than the effects of mediator-outcome when adjusting for the mediator in the absence of unobserved confounders, while the biases were more sensitive to the variation of effects of mediator-outcome than those of exposure-mediator in the presence of an unobserved confounder.

Confounding in statistical mediation analysis: What it is and how to address it

Psychology researchers are often interested in mechanisms underlying how randomized interventions affect outcomes such as substance use and mental health. Mediation analysis is a common statistical method for investigating psychological mechanisms that has benefited from exciting new methodological improvements over the last 2 decades. One of the most important new developments is methodology for estimating causal mediated effects using the potential outcomes framework for causal inference. Potential outcomes-based methods developed in epidemiology and statistics have important implications for understanding psychological mechanisms. We aim to provide a concise introduction to and illustration of these new methods and emphasize the importance of confounder adjustment. First, we review the traditional regression approach for estimating mediated effects. Second, we describe the potential outcomes framework. Third, we define what a confounder is and how the presence of a confounder can provide misleading evidence regarding mechanisms of interventions. Fourth, we describe experimental designs that can help rule out confounder bias. Fifth, we describe new statistical approaches to adjust for measured confounders of the mediator-outcome relation and sensitivity analyses to probe effects of unmeasured confounders on the mediated effect. All approaches are illustrated with application to a real counseling intervention dataset. Counseling psychologists interested in understanding the causal mechanisms of their interventions can benefit from incorporating the most up-to-date techniques into their mediation analyses. (PsycINFO Database Record

Bayesian sensitivity analysis for unmeasured confounding in causal mediation analysis

Causal mediation analysis techniques enable investigators to examine whether the effect of the exposure on an outcome is mediated by some intermediate variable. Motivated by a data example from epidemiology, we consider estimation of natural direct and indirect effects on a survival outcome. An important concern is bias from confounders that may be unmeasured. Estimating natural direct and indirect effects requires an elaborate series of assumptions in order to identify the target quantities. The analyst must carefully measure and adjust for important predictors of the exposure, mediator and outcome. Omitting important confounders may bias the results in a way that is difficult to predict. In recent years, several methods have been proposed to explore sensitivity to unmeasured confounding in mediation analysis. However, many of these methods limit complexity by relying on a handful of sensitivity parameters that are difficult to interpret, or alternatively, by assuming that specific patterns of unmeasured confounding are absent. Instead, we propose a simple Bayesian sensitivity analysis technique that is indexed by four bias parameters. Our method has the unique advantage that it is able to simultaneously assess unmeasured confounding in the mediator–outcome, exposure–outcome and exposure–mediator relationships. It is a natural Bayesian extension of the sensitivity analysis methodologies of VanderWeele, which have been widely used in the epidemiology literature. We present simulation findings, and additionally, we illustrate the method in an epidemiological study of mortality rates in criminal offenders from British Columbia.

Do baby teeth really matter? Changing parental perception and increasing dental care utilization for young children

INTRODUCTION

Parent/caregivers' inability to recognize the importance of baby teeth has been associated with inadequate self-management of children's oral health (i.e. lower likelihood of preventive dental visits) which may result in dental caries and the need for more expensive caries-related restorative treatment under general anesthesia. Health behavior theories aid researchers in understanding the impact and effectiveness of interventions on changing health behaviors and health outcomes. One example is the Common-Sense Model of Self-Regulation (CSM) which focuses on understanding an individual's illness perception (i.e. illness and treatment representations), and subsequently has been used to develop behavioral interventions to change inaccurate perceptions and describe the processes involved in behavior change.

METHODS

We present two examples of randomized clinical trials that are currently testing oral health behavioral interventions to change parental illness perception and increase dental utilization for young children disproportionately impacted by dental caries in elementary schools and pediatric primary care settings. Additionally, we compared empiric data regarding parent/caregiver perception of the chronic nature of dental caries (captured by the illness perception questionnaire revised for dental: IPQ-RD constructs: identity, consequences, control, timeline, illness coherence, emotional representations) between parent/caregivers who did and did not believe baby teeth were important.

RESULTS

Caregivers who believed that baby teeth don't matter had significantly (P<0.05) less accurate perception in the majority of the IPQ-RD constructs (except timeline construct) compared to caregivers who believed baby teeth do matter.

CONCLUSION

These findings support our CSM-based behavioral interventions to modify caregiver caries perception, and improve dental utilization for young children.

Causal mechanisms in the clinical course and treatment of back pain

In recent years, there has been increasing interest in studying causal mechanisms in the development and treatment of back pain. The aim of this article is to provide an overview of our current understanding of causal mechanisms in the field. In the first section, we introduce key concepts and terminology. In the second section, we provide a brief synopsis of systematic reviews of mechanism studies relevant to the clinical course and treatment of back pain. In the third section, we reflect on the findings of our review to explain how understanding causal mechanisms can inform clinical practice and the implementation of best practice. In the final sections, we introduce contemporary methodological advances, highlight the key assumptions of these methods, and discuss future directions to advance the quality of mechanism-related studies in the back pain field.

Causal Mediation Analysis for the Cox Proportional Hazards Model with a Smooth Baseline Hazard Estimator

An important problem within the social, behavioral, and health sciences is how to partition an exposure effect (e.g. treatment or risk factor) among specific pathway effects and to quantify the importance of each pathway. Mediation analysis based on the potential outcomes framework is an important tool to address this problem and we consider the estimation of mediation effects for the proportional hazards model in this paper. We give precise definitions of the total effect, natural indirect effect, and natural direct effect in terms of the survival probability, hazard function, and restricted mean survival time within the standard two-stage mediation framework. To estimate the mediation effects on different scales, we propose a mediation formula approach in which simple parametric models (fractional polynomials or restricted cubic splines) are utilized to approximate the baseline log cumulative hazard function. Simulation study results demonstrate low bias of the mediation effect estimators and close-to-nominal coverage probability of the confidence intervals for a wide range of complex hazard shapes. We apply this method to the Jackson Heart Study data and conduct sensitivity analysis to assess the impact on the mediation effects inference when the no unmeasured mediator-outcome confounding assumption is violated.

A framework for Bayesian nonparametric inference for causal effects of mediation

We propose a Bayesian non-parametric (BNP) framework for estimating causal effects of mediation, the natural direct, and indirect, effects. The strategy is to do this in two parts. Part 1 is a flexible model (using BNP) for the observed data distribution. Part 2 is a set of uncheckable assumptions with sensitivity parameters that in conjunction with Part 1 allows identification and estimation of the causal parameters and allows for uncertainty about these assumptions via priors on the sensitivity parameters. For Part 1, we specify a Dirichlet process mixture of multivariate normals as a prior on the joint distribution of the outcome, mediator, and covariates. This approach allows us to obtain a (simple) closed form of each marginal distribution. For Part 2, we consider two sets of assumptions: (a) the standard sequential ignorability (Imai et al., 2010) and (b) weakened set of the conditional independence type assumptions introduced in Daniels et al. (2012) and propose sensitivity analyses for both. We use this approach to assess mediation in a physical activity promotion trial.

Assessing natural direct and indirect effects for a continuous exposure and a dichotomous outcome

Recent advances in the literature on mediation have extended from traditional linear structural equation modeling approach to causal mediation analysis using potential outcomes framework. Pearl proposed a mediation formula to calculate expected potential outcomes used in the natural direct and indirect effects definition under the key sequential ignorability assumptions. Current methods mainly focused on binary exposure variables, and in this article, this approach is further extended to settings in which continuous exposures may be of interest. Focusing on a dichotomous outcome, we give precise definitions of the natural direct and indirect effects on both the risk difference and odds ratio scales utilizing the empirical joint distribution of the exposure and baseline covariates from the whole sample analysis population. A mediation-formula based approach is proposed to estimate the corresponding causal quantities. Simulation study is conducted to assess the statistical properties of the proposed method and we illustrate our approach by applying it to the Jackson Heart Study to estimate the mediation effects of diabetes on the relation between obesity and chronic kidney disease. Sensitivity analysis is performed to assess the impact of violation of no unmeasured mediator-outcome confounder assumption.

Causal mediation analysis with a latent mediator

Health researchers are often interested in assessing the direct effect of a treatment or exposure on an outcome variable, as well as its indirect (or mediation) effect through an intermediate variable (or mediator). For an outcome following a nonlinear model, the mediation formula may be used to estimate causally interpretable mediation effects. This method, like others, assumes that the mediator is observed. However, as is common in structural equations modeling, we may wish to consider a latent (unobserved) mediator. We follow a potential outcomes framework and assume a generalized structural equations model (GSEM). We provide maximum-likelihood estimation of GSEM parameters using an approximate Monte Carlo EM algorithm, coupled with a mediation formula approach to estimate natural direct and indirect effects. The method relies on an untestable sequential ignorability assumption; we assess robustness to this assumption by adapting a recently proposed method for sensitivity analysis. Simulation studies show good properties of the proposed estimators in plausible scenarios. Our method is applied to a study of the effect of mother education on occurrence of adolescent dental caries, in which we examine possible mediation through latent oral health behavior.

What matters most: quantifying an epidemiology of consequence

Risk factor epidemiology has contributed to substantial public health success. In this essay, we argue, however, that the focus on risk factor epidemiology has led epidemiology to ever increasing focus on the estimation of precise causal effects of exposures on an outcome at the expense of engagement with the broader causal architecture that produces population health. To conduct an epidemiology of consequence, a systematic effort is needed to engage our science in a critical reflection both about how well and under what conditions or assumptions we can assess causal effects and also on what will truly matter most for changing population health. Such an approach changes the priorities and values of the discipline and requires reorientation of how we structure the questions we ask and the methods we use, as well as how we teach epidemiology to our emerging scholars.