Commentary: Mediation Analyses in the Real World.

SAS Macro for Causal Mediation Analysis with Survival Data

Mediation analysis is an important statistical method in prevention research, as it can be used to determine effective intervention components. Traditional mediation analysis defines direct and indirect effects in terms of linear regression coefficients. It is unclear how these traditional effects are estimated in settings with binary variables. An important recent methodological advancement in the mediation analysis literature is the development of the causal mediation analysis framework. Causal mediation analysis defines causal effects as the difference between two potential outcomes. These definitions can be applied to any mediation model to estimate natural direct and indirect effects, including models with binary variables and an exposure–mediator interaction. This paper aims to clarify the similarities and differences between the causal and traditional effect estimates for mediation models with a binary mediator and a binary outcome. Causal and traditional mediation analyses were applied to an empirical example to demonstrate these similarities and differences. Causal and traditional mediation analysis provided similar controlled direct effect estimates, but different estimates of the natural direct effects, natural indirect effects, and total effect. Traditional mediation analysis methods do not generalize well to mediation models with binary variables, while the natural effect definitions can be applied to any mediation model. Causal mediation analysis is therefore the preferred method for the analysis of mediation models with binary variables.

Could the New England Journal of Medicine Be Biased Against Arthroscopic Knee Surgery? Part 2

Since its introduction in the twentieth century, null hypothesis significance testing (NHST), a hybrid of significance testing (ST) advocated by Fisher and null hypothesis testing (NHT) developed by Neyman and Pearson, has become widely adopted but has also been a source of debate. The principal alternative to such testing is estimation with point estimates and confidence intervals (CI). Our aim was to estimate time trends in NHST, ST, NHT and CI reporting in abstracts of major medical and epidemiological journals. We reviewed 89,533 abstracts in five major medical journals and seven major epidemiological journals, 1975-2014, and estimated time trends in the proportions of abstracts containing statistical inference. In those abstracts, we estimated time trends in the proportions relying on NHST and its major variants, ST and NHT, and in the proportions reporting CIs without explicit use of NHST (CI-only approach). The CI-only approach rose monotonically during the study period in the abstracts of all journals. In Epidemiology abstracts, as a result of the journal's editorial policy, the CI-only approach has always been the most common approach. In the other 11 journals, the NHST approach started out more common, but by 2014, this disparity had narrowed, disappeared or reversed in 9 of them. The exceptions were JAMA, New England Journal of Medicine, and Lancet abstracts, where the predominance of the NHST approach prevailed over time. In 2014, the CI-only approach is as popular as the NHST approach in the abstracts of 4 of the epidemiology journals: the American Journal of Epidemiology (48%), the Annals of Epidemiology (55%), Epidemiology (79%) and the International Journal of Epidemiology (52%). The reporting of CIs without explicitly interpreting them as statistical tests is becoming more common in abstracts, particularly in epidemiology journals. Although NHST is becoming less popular in abstracts of most epidemiology journals studied and some widely read medical journals, it is still very common in the abstracts of other widely read medical journals, especially in the hybrid form of ST and NHT in which p values are reported numerically along with declarations of the presence or absence of statistical significance.

Celiac Disease: The Endocrine Connection

Annals for Educators - 21 April 2020.

Lapses at the New England Journal of Medicine

BackgroundThe CHIC study (COVID-19 High-intensity Immunosuppression in Cytokine storm syndrome) is a quasi-experimental treatment study exploring immunosuppressive treatment versus supportive treatment only in patients with COVID-19 with life-threatening hyperinflammation. Causal...

Mediation analysis is widely used in psychology to assess how an independent variable transmits its causal effect on an outcome both directly and indirectly through intermediary variables known as mediators. Causal mediation analysis addresses numerous criticisms of product-of-coefficients approach, often regarded as the primary method for estimating indirect effects in psychological research. However, navigating causal mediation analysis, especially in settings with multiple mediators, can be challenging for those unfamiliar with its concepts, assumptions, and estimation strategies. In this tutorial, we therefore offer a comprehensive guide to conducting causal mediation analysis with two mediators across three data-generating mechanisms: setups with causally dependent mediators, independent mediators, and noncausally dependent mediators. For each of these mechanisms, we provide formal mathematical definitions and assumptions for the natural direct and indirect effects, along with less technical explanations of these concepts. We also provide R and Stata codes for estimating the natural direct effect, the joint natural indirect effect, and the path-specific natural indirect effects using four different estimators: the imputation approach, the extended imputation approach, the inverse probability weighted approach, and the extended quasi-Bayesian Monte Carlo approach. Additionally, we illustrate each of these methods with examples from the International Dating Violence Study. This tutorial aims to equip applied researchers in psychology with all the necessary tools to conduct causal mediation analysis involving two mediators across various multiple mediators setups. (PsycInfo Database Record (c) 2025 APA, all rights reserved).

Epidemiology and risk factors of needle stick injuries

In a recent manuscript, VanderWeele and Vansteelandt (American Journal of Epidemiology, 2010,172:1339-1348) (hereafter VWV) build on results due to Judea Pearl on causal mediation analysis and derive simple closed-form expressions for so-called natural direct and indirect effects in an odds ratio context for a binary outcome and a continuous mediator. The expressions obtained by VWV make two key simplifying assumptions: The mediator is normally distributed with constant variance,The binary outcome is rare. Assumption A may not be appropriate in settings where, as can happen in routine epidemiologic applications, the distribution of the mediator variable is highly skew. However, in this note, the author establishes that under a key assumption of "no mediator-exposure interaction" in the logistic regression model for the outcome, the simple formulae of VWV continue to hold even when the normality assumption of the mediator is dropped. The author further shows that when the "no interaction" assumption is relaxed, the formula of VWV for the natural indirect effect in this setting continues to apply when assumption A is also dropped. However, an alternative formula to that of VWV for the natural direct effect is required in this context and is provided in an appendix. When the disease is not rare, the author replaces assumptions A and B with an assumption C that the mediator follows a so-called Bridge distribution in which case simple closed-form formulae are again obtained for the natural direct and indirect effects.

While birthweight of offspring is associated with pre-pregnancy body mass index (BMI) and later risk of obesity, its mediating effect between the association of maternal pre-pregnancy BMI and offspring's childhood anthropometrics has rarely been investigated. This study aimed to examine whether offspring birthweight is a mediator in the association between pre-pregnancy BMI and offspring's childhood anthropometrics. The study included 1,618 mother-child pairs from the Australian Longitudinal Study on Women's Health and Mothers and their Children's Health Study. Children's anthropometrics [mean age 8.6 (s.d. =3.0) years] were calculated from the mothers' self-reported child weight and height measures. G-computation was used to estimate the natural direct and indirect (via birthweight) effects of pre-pregnancy BMI. In the fully adjusted model for maternal sociodemographic and lifestyle factors, the natural direct effects of pre-pregnancy obesity on child BMI-for-age, height-for-age, weight-for-age and weight-for-height outcomes were, β (95% confidence interval, CI), 0.75 (0.55, 0.95), 0.13 (-0.07, 0.32), 0.62 (0.44, 0.80) and 0.57 (0.24, 0.90), respectively. The corresponding natural indirect effects were 0.04 (-0.04, 0.12), -0.01 (-0.09, 0.07), -0.01 (-0.08, 0.07) and 0.09 (-0.05, 0.23). Similar results were observed for pre-pregnancy overweight and pre-pregnancy BMI as a continuous scale. Most of the effect of pre-pregnancy obesity on childhood weight-related anthropometric outcomes appears to be via a direct effect, not mediated through offspring's birthweight.

This study extends mediation analysis techniques to explore whether and to what extent differential access to a medical home explains the black/white disparity in unmet healthcare needs among children with special healthcare needs (CSHCN). Data were obtained from the 2007 National Survey of Children's Health, with analyses limited to non-Hispanic white and black CSHCN (n=14,677). The counterfactual approach to mediation analysis was used to estimate odds ratios for the natural direct and indirect effects of race on unmet healthcare needs. Overall, 43.0% of white CSHCN and 60.4% of black CSHCN did not have a medical home. Additionally, 8.8% of white CSHCN and 15.3% of black CSHCN had unmet healthcare needs. The natural indirect effect indicates that the odds of unmet needs among black CSHCN are elevated by approximately 20% as a result of their current level of access to the medical home rather than access at a level equal to white CSHCN (OR(NIE)=1.2, 95% CI=1.1, 1.3). The natural direct effect indicates that even if black CSHCN had the same level of access to a medical home as white CSHCN, blacks would still have 60% higher odds of unmet healthcare needs than whites (OR(NDE)=1.6, 95% CI=1.1, 2.4). The racial disparity in unmet healthcare needs among CSHCN is only partially explained by disparities in having a medical home. Ensuring all CSHCN have equal access to a medical home may reduce the racial disparity in unmet needs, but will not completely eliminate it.

Mediation analysis provides an attractive causal inference framework to decompose the total effect of an exposure on an outcome into natural direct effects and natural indirect effects acting through a mediator. For binary outcomes, mediation analysis methods have been developed using logistic regression when the binary outcome is rare. These methods will not hold in practice when a disease is common. In this paper, we develop mediation analysis methods that relax the rare disease assumption when using logistic regression. We calculate the natural direct and indirect effects for common diseases by exploiting the relationship between logit and probit models. Specifically, we derive closed-form expressions for the natural direct and indirect effects on the odds ratio scale. Mediation models for both continuous and binary mediators are considered. We demonstrate through simulation that the proposed method performs well for common binary outcomes. We apply the proposed methods to analyze the Normative Aging Study to identify DNA methylation sites that are mediators of smoking behavior on the outcome of obstructed airway function.

The JAMA and NEJM Rulings and Their Impact on the Sanctity of Confidential Peer Review