Estimation of Controlled Direct Effects in Longitudinal Mediation Analyses with Latent Variables in Randomized Studies

Abstract

In a randomized study with longitudinal data on a mediator and outcome, estimating the direct effect of treatment on the outcome at a particular time requires adjusting for confounding of the association between the outcome and all preceding instances of the mediator. When the confounders are themselves affected by treatment, standard regression adjustment is prone to severe bias. In contrast, G-estimation requires less stringent assumptions than path analysis using SEM to unbiasedly estimate the direct effect even in linear settings. In this article, we propose a G-estimation method to estimate the controlled direct effect of treatment on the outcome, by adapting existing G-estimation methods for time-varying treatments without mediators. The proposed method can accommodate continuous and noncontinuous mediators, and requires no models for the confounders. Unbiased estimation only requires correctly specifying a mean model for either the mediator or the outcome. The method is further extended to settings where the mediator or outcome, or both, are latent, and generalizes existing methods for single measurement occasions of the mediator and outcome to longitudinal data on the mediator and outcome. The methods are utilized to assess the effects of an intervention on physical activity that is possibly mediated by motivation to exercise in a randomized study.     

Five‐ to twelve‐year‐olds' control of movement velocity in a dynamic collision avoidance task

We investigated age‐related differences in a dynamic collision avoidance task that bears a resemblance to pedestrian road crossing. Five‐ to seven‐year‐old children, ten‐ to twelve‐year‐old children and adults were instructed to push a doll across a small‐scale road between two toy vehicles, which approached one after the other. We analysed the number of attempted crossings, the number of collisions, movement onset times and movement velocity control. The youngest children attempted to cross less often, but collided more frequently than the adults. This age effect could be attributed to differences in the way the children and adults controlled movement velocity. The youngest children attained the velocity that was required for safe travel too late, particularly when the gaps between the toy vehicles were small. The age differences in movement onset strategies were less clear‐cut. The findings are discussed within a framework that proposes distinct roles of vision in action planning and action production.     

Stigma,Attitudes, and Help‐Seeking Intentions for Psychological Problems in Relation to Regional Suicide Rates

In this ecological study, we investigated whether help‐seeking related to stigma, intentions, and attitudes toward suicide are associated with the suicide rates of 20 regions within the Netherlands and Belgium. Significant associations were found between regional suicide rates and the intention to seek informal help (β = ?1.47, p = .001), self‐stigma (β = 1.33, p = .038), and shame (β = .71, p = .030). The association between self‐stigma and suicide rate was mediated by intentions to seek informal help. These results suggest that to promote suicide prevention at the level of the regional population, stigma, shame, and intentions to seek help should be targeted in the public domain.     

On the generality of the affective Simon effect

In affective Simon studies, participants are to select between a positive and negative response on the basis of a nonaffective stimulus feature (i.e., relevant stimulus feature) while ignoring the valence of the presented stimuli (i.e., irrelevant stimulus feature). De Houwer and Eelen (1998) showed that the time to select the correct response is influenced by the match between the valence of the response and the (irrelevant) valence of the stimulus. In the affective Simon studies that have been reported until now, only words were used as stimuli and the relevant stimulus feature was always the grammatical category of the words. We report four experiments in which we examined the generality of the affective Simon effect. Significant affective Simon effects were found when the semantic category, grammatical category, and letter-case of words was relevant, when the semantic category of photographed objects was relevant, and when participants were asked to give nonverbal approach or avoidance responses on the basis of the grammatical category of words. Results also showed that the magnitude of the affective Simon effect depended on the nature of the relevant feature.     

The relation between goal adjustment,goal disturbance,and mental well-being among persons with multiple sclerosis

Objective: This study investigated the role of goal adjustment, i.e. disengaging from blocked goals and reengaging into alternative goals, in mental well-being and goal disturbance in persons with multiple sclerosis (MS).

Design: A cross-sectional design was used with self-report data from questionnaires and Personal Project Analysis (PPA).

Main outcome measures: Dependent variables were mental well-being, indicated by depression/anxiety (HADS; Hospital Anxiety and Depression Scale) and mental functioning (SF-36; Short Form Health Survey), and goal disturbance, indicated by goal manageability and goal interference (PPA). Independent variables were patient-reported physical impairment (SF-36) and goal disengagement and reengagement (GAS; Goal Adjustment Scale).

Results: Higher goal reengagement was associated with better mental well-being, but unrelated to goal disturbance. Goal disengagement only showed a negative association with anxiety. High disengagement was associated with lower goal interference but only for those also scoring high on reengagement. Goal adjustment did not buffer the effects of physical impairment on mental well-being and goal disturbance. Contrary to expectations, higher goal reengagement increased the association between physical impairment and goal interference.

Conclusion: Although goal reengagement is associated with better mental well-being in persons with MS, it might also strengthen the perceived effect of physical impairment on goal interference.