Most investigations in the social and health sciences aim to understand the directional or causal relationship between a treatment or risk factor and outcome. Given the multitude of pathways through which the treatment or risk factor may affect the outcome, there is also an interest in decomposing the effect of a treatment of risk factor into “direct” and “mediated” effects. For example, child's socioeconomic status (risk factor) may have a direct effect on the risk of death (outcome) and an effect that may be mediated through the adulthood socioeconomic status (mediator). Building on the potential outcome framework for causal inference, we develop a Bayesian approach for estimating direct and mediated effects in the context of a dichotomous mediator and dichotomous outcome, which is challenging as many parameters cannot be fully identified. We first define principal strata corresponding to the joint distribution of the observed and counterfactual values of the mediator, and define associate, dissociative, and mediated effects as functions of the differences in the mean outcome under differing treatment assignments within the principal strata. We then develop the likelihood properties and calculate nonparametric bounds of these causal effects assuming randomized treatment assignment. Because likelihood theory is not well developed for nonidentifiable parameters, we consider a Bayesian approach that allows the direct and mediated effects to be expressed in terms of the posterior distribution of the population parameters of interest. This range can be reduced by making further assumptions about the parameters that can be encoded in prior distribution assumptions. We perform sensitivity analyses by using several prior distributions that make weaker assumptions than monotonicity or the exclusion restriction. We consider an application that explores the mediating effects of adult poverty on the relationship between childhood poverty and risk of death.

Patterns of symptom clustering in midlife women may suggest common underlying mechanisms or may identify women at risk of adverse health outcomes or, conversely, likely to experience healthy aging. This paper assesses symptom clustering in the Study of Women’s Health Across the Nation (SWAN) longitudinally by stage of reproductive aging and estimates the probability of women experiencing specific symptom clusters. We also evaluate factors that influence the likelihood of specific symptom clusters and assess whether symptom clustering is associated with women’s self-reported health status. This analysis includes 3289 participants in the multiethnic SWAN cohort who provided information on 58 symptoms reflecting a broad range of physical, psychological and menopausal symptoms at baseline and 7 follow-up visits over 16 years. We conducted latent transition analyses to assess symptom clustering and to model symptomatology across the menopausal transition (pre, early peri-, late peri- and post-menopausal). Joint multinomial logistic regression models were used to identify demographic characteristics associated with premenopausal latent class membership. A partial proportional odds regression model was used to assess the association between latent class membership and self-reported health status. We identified six latent classes that ranged from highly symptomatic (LC1) across most measured symptoms, to moderately symptomatic across most measured symptoms (LC2), to moderately symptomatic for a subset of symptoms (vasomotor symptoms, pain, fatigue, sleep disturbances and physical health symptoms) (LC3 and LC5) with one class (LC3) including interference in life activities because of physical health symptoms, to numerous milder symptoms, dominated by fatigue and psychological symptoms (LC4), to relatively asymptomatic (LC6). In pre-menopause, 10% of women were classified in LC1, 16% in LC2, 14% in LC3 and LC4, 26% in LC5, and 20% in LC6. Intensity of vasomotor and urogenital symptoms as well as sexual desire) differed minimally by latent class. Classification into the two most symptomatic classes was strongly associated with financial strain, White race/ethnicity, obesity and smoking status. Over time, women were most likely to remain within the same latent class as they transitioned through menopause stages (range 39–76%), although some women worsened or improved. The probability of moving between classes did not differ substantially by menopausal stage. Women in the highly symptomatic classes more frequently rated their health as fair to poor compared to women in the least symptomatic class. Clear patterns of symptom clustering were present early in midlife, tended to be stable over time, and were strongly associated with self-perceived health. Notably, vasomotor symptoms tended to cluster with sleep disturbances and fatigue, were present in each of the moderate to highly symptomatic classes, but were not a defining characteristic of the symptom clusters. Clustering of midlife women by symptoms may suggest common underlying mechanisms amenable to interventions. Given that one-quarter of midlife women were highly or moderately symptomatic across all domains in the pre-menopause, addressing symptom burden in early midlife is likely critical to ameliorating risk in the most vulnerable populations.

Firearms are the most commonly used weapon to commit homicide in the U.S. Virtually all firearms enter the public marketplace through a federal firearms licensee (FFL): a store or individual licensed by the federal government to sell firearms. Whether FFLs contribute to gun-related homicide in areas where they are located, in which case FFLs may be a homicide risk factor that can be modified, is not known.

Because of the time and expense required to obtain clinical outcomes of interest, such as functional limitations or death, clinical trials often focus the effects of treatment on earlier and more easily obtained surrogate markers. Preliminary work to define surrogates focused on the fraction of a treatment effect “explained” by a marker in a regression model, but as notions of causality have been formalized in the statistical setting, formal definitions of high-quality surrogate markers have been developed in the causal inference framework, using either the “causal effect” or “causal association” settings. In the causal effect setting, high-quality surrogate markers have a large fraction of the total treatment effect explained by the effect of the treatment on the marker net of the treatment on the outcome. In the causal association setting, high-quality surrogate markers have large treatment effects on the outcome when there are large treatment effects on the marker, and small effects on the outcome when there are small effects on the marker. A particularly important feature of a surrogate marker is that the direction of a treatment effect be the same for both the marker and the outcome. Settings in which the marker and outcome are positively associated but the marker and outcome have beneficial and harmful or harmful and beneficial treatment effects, respectively, have been referred to as “surrogate paradoxes”. If this outcome always occurs, it is not problematic; however, as correlations among the outcome, marker, and their treatment effects weaken, it may occur for some trials and not for others, leading to potentially incorrect conclusions, and real-life examples that shortened thousands of lives are unfortunately available. We propose measures for assessing the risk of the surrogate paradox using the meta-analytic causal association framework, which allows us to focus on the probability that a given treatment will yield treatment effect in different directions between the marker and the outcome, and to determine the size of a beneficial effect of the treatment on the marker required to minimize the risk of a harmful effect of the treatment on the outcome. We provide simulations and consider two applications.