Clarifying causal mediation analysis for the applied researcher: Defining effects based on what we want to learn.

AbstractWith reference to causal mediation analysis, a parametric expression for natural direct and indirect effects is derived for the setting of a binary outcome with a binary mediator, both modelled via a logistic regression. The proposed effect decomposition operates on the odds ratio scale and does not require the outcome to be rare. It generalizes the existing ones, allowing for interactions between both the exposure and the mediator and the confounding covariates. The derived parametric formulae are flexible, in that they readily adapt to the two different natural effect decompositions defined in the mediation literature. In parallel with results derived under the rare outcome assumption, they also outline the relationship between the causal effects and the correspondent pathway-specific logistic regression parameters, isolating the controlled direct effect in the natural direct effect expressions. Formulae for standard errors, obtained via the delta method, are also given. An empirical application to data coming from a microfinance experiment performed in Bosnia and Herzegovina is illustrated.

Download Full-text

Factors explaining socio-economic inequalities in survival from colon cancer: a causal mediation analysis

Cancer Epidemiology Biomarkers & Prevention ◽

10.1158/1055-9965.epi-21-0222 ◽

2021 ◽

pp. cebp.0222.2021

Author(s):

Nina Afshar ◽

S. Ghazaleh Dashti ◽

Luc te Marvelde ◽

Tony Blakely ◽

Andrew Haydon ◽

...

Keyword(s):

Colon Cancer ◽

Mediation Analysis ◽

Causal Mediation ◽

Causal Mediation Analysis ◽

Economic Inequalities

Download Full-text

Bayesian sensitivity analysis for unmeasured confounding in causal mediation analysis

Statistical Methods in Medical Research ◽

10.1177/0962280217729844 ◽

2017 ◽

Vol 28 (2) ◽

pp. 515-531 ◽

Cited By ~ 2

Author(s):

Lawrence C McCandless ◽

Julian M Somers

Keyword(s):

Sensitivity Analysis ◽

Mediation Analysis ◽

Indirect Effects ◽

Direct And Indirect Effects ◽

Unmeasured Confounding ◽

Intermediate Variable ◽

Causal Mediation ◽

Important Concern ◽

Analysis Technique ◽

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.

Download Full-text

Prying Open the Black Box of Causality - A Causal Mediation Analysis Test of Procedural Justice Policing

10.31235/osf.io/9x7n6 ◽

2017 ◽

Cited By ~ 1

Author(s):

Krisztián Pósch

Keyword(s):

Procedural Justice ◽

Treatment Effect ◽

Mediation Analysis ◽

Black Box ◽

Mediation Effects ◽

Causal Mediation ◽

Treatment Implementation ◽

Causal Mediation Analysis ◽

The Impact ◽

Sense Of Power

Objectives: Review causal mediation analysis as a method for estimating and assessing direct and indirect effects in experimental criminology. Test procedural justice theory by examining the extent to which procedural justice mediates the impact of contact with the police on various outcomes. Apply causal mediation analysis to better interpret data from a field experiment that had suffered from a particular type of implementation failure.Methods: Data from a block-randomised controlled trial of procedural justice policing (the Scottish Community Engagement Trial) were analysed. All constructs were measured using surveys distributed during roadside police checks. The treatment implementation was assessed by analysing the treatment effect consistency and heterogeneity. Causal mediation analysis and sensitivity analysis were used to assess the mediating role of procedural justice.Results: First, the treatment effect was consistent and fairly homogeneous, indicating that the systematic variation in the study is attributable to the design. Second, procedural justice acts as a mediator channelling the treatment’s effect towards normative alignment (NIE=-0.207), duty to obey (NIE=-0.153), sense of power (NIE=-0.078), and social identity (NIE=-0.052), all of which are moderately robust to unmeasured confounding. The NIEs for risk of sanction and personal morality were highly sensitive, while for coerced obligation and sense of power they were non-significant. Conclusions: Causal mediation analysis is a versatile tool that can salvage experiments with systematic yet ambiguous treatment effects by allowing researchers to “pry open” the black box of causality. Most of the theoretical propositions of procedural justice policing were supported. Future studies are needed with more discernible causal mediation effects.

Download Full-text

Maternal obesity before pregnancy predicts offspring blood pressure at 18 years of age: A causal mediation analysis

10.1101/2020.11.22.20236398 ◽

2020 ◽

Author(s):

Nicole Brunton ◽

Brenden Dufault ◽

Allison Dart ◽

Meghan B. Azad ◽

Jonathan M McGavock

Keyword(s):

Blood Pressure ◽

Mediation Analysis ◽

Elevated Blood Pressure ◽

Childhood And Adolescence ◽

Elevated Blood ◽

Causal Mediation ◽

Increased Risk ◽

Causal Mediation Analysis ◽

Maternal Bmi ◽

Bmi Trajectory

ABSTRACTImportanceHypertension is the second most common pediatric chronic disease in Westernized countries. Understanding the natural history of hypertension is key to identifying prevention strategies.ObjectiveExamine the relationship between maternal pre-pregnancy body mass index (BMI) and offspring blood pressure at 18 years and the mediating role of growth throughout childhood and adolescence.Design, Setting, and ParticipantsWe performed multivariable regression and causal mediation analyses within 3217 mother - offspring pairs from the Avon Longitudinal Study of Parents and Children (ALSAPC) prospective birth cohort. Latent trajectory analysis (LTA) was used to quantify the mediating variable of offspring BMI from 7 to 18 years of age.ExposuresThe main exposure was maternal pre-pregnancy BMI. Analyses were adjusted for relevant confounders including maternal education, maternal blood pressure, and weeks gestation at delivery.Main Outcomes and MeasuresThe main outcome was offspring blood pressure at 18 years of age categorized as normal (SBP < 120 mmHg or DBP < 80mmHg) or elevated (SBP ≥ 120 mmHg or DBP ≥ 80 mmHg) as per the 2017 American Academy of Pediatrics guidelines.ResultsAt 18 years of age, among 3217 offspring, 676 (21%) were overweight or obese, 865 (27%) had elevated blood pressure, and 510 (16%) were hypertensive. LTA identified five distinct offspring BMI trajectories. Multivariate logistic regression revealed that for every 1 unit increase in maternal BMI the risk of elevated blood pressure at 18 years of age increased by 5% (aOR: 1.05, 95% CI: 1.03 – 1.07; p <0.001) and this effect was reduced after adjusting for offspring BMI trajectory (aOR: 1.03, 95% CI: 1.00 – 1.05; p = 0.017). Causal mediation analysis confirmed offspring BMI trajectory as a mediator accounting for 46% of the total effect of maternal BMI on elevated offspring blood pressure (aOR 1.22; 95% CI: 1.07-1.39).Conclusion and RelevanceMaternal BMI prior to pregnancy is associated with an increased risk of elevated blood pressure in offspring at 18 years of age and is mediated, in part, by offspring BMI trajectory throughout childhood and adolescence.

Download Full-text