Content uploaded by Tyson S Barrett
Author content
All content in this area was uploaded by Tyson S Barrett on Mar 22, 2018
Content may be subject to copyright.
A preview of the PDF is not available
Marginal Mediation Analysis: A New Framework for Interpretable Mediated Effects
Abstract and Figures
Mediation analysis is built to answer not only if one variable affects another, but how the effect takes place. However, it lacks interpretable effect size estimates in situations where the mediator (an intermediate variable) and/or the outcome is categorical or otherwise non-normally distributed. By integrating a powerful approach known as average marginal effects within mediation analysis—termed Marginal Mediation Analysis (MMA)—the issues regarding categorical mediators and/or outcomes are, in large part, resolved. This new approach allows the estimation of the indirect effects (those effects of the predictor that affect the outcome through the mediator) that are interpreted in the same way as mediation analysis with continuous, normally-distributed mediators and outcomes. This also, in turn, resolves the troubling situation wherein the indirect plus the direct effect does not equal the total effect (i.e., the total effect does not equal the total effect). By offering this information in mediation, interventionists and lawmakers can better understand where efforts and resources can make the greatest impact.
This project presents the development and the software of MMA, describes the evaluation of its performance, and reports an application of MMA to health data. The approach is successful in several aspects: 1) the software works across a wide variety of situations as the {MarginalMediation} R package; 2) MMA performed well and was statistically powered much like other mediation analysis approaches; and 3) the application demonstrated the increased amount of interpretable information that is provided in contrast to other approaches.
Figures - uploaded by Tyson S Barrett
Author content
All figure content in this area was uploaded by Tyson S Barrett
Content may be subject to copyright.
ResearchGate has not been able to resolve any citations for this publication.
Purpose:
Generalization of perceptual learning has received limited attention in listener adaptation studies with dysarthric speech. This study investigated whether adaptation to a talker with dysarthria could be predicted by the nature of the listener's prior familiarization experience, specifically similarity of perceptual features, and level of intelligibility.
Method:
Following an intelligibility pretest involving a talker with ataxic dysarthria, 160 listeners were familiarized with 1 of 7 talkers with dysarthria-who differed from the test talker in terms of perceptual similarity (same, similar, dissimilar) and level of intelligibility (low, mid, high)-or a talker with no neurological impairment (control). Listeners then completed an intelligibility posttest on the test talker.
Results:
All listeners benefited from familiarization with a talker with dysarthria; however, adaptation to the test talker was superior when the familiarization talker had similar perceptual features and reduced when the familiarization talker had low intelligibility.
Conclusion:
Evidence for both generalization and specificity of learning highlights the differential value of listeners' prior experiences for adaptation to, and improved understanding of, a talker with dysarthria. These findings broaden our theoretical knowledge of adaptation to degraded speech, as well as the clinical application of training paradigms that exploit perceptual processes for therapeutic gain.
Purpose:
The perception of rhythm cues plays an important role in recognizing spoken language, especially in adverse listening conditions. Indeed, this has been shown to hold true even when the rhythm cues themselves are dysrhythmic. This study investigates whether expertise in rhythm perception provides a processing advantage for perception (initial intelligibility) and learning (intelligibility improvement) of naturally dysrhythmic speech, dysarthria.
Method:
Fifty young adults with typical hearing participated in 3 key tests, including a rhythm perception test, a receptive vocabulary test, and a speech perception and learning test, with standard pretest, familiarization, and posttest phases. Initial intelligibility scores were calculated as the proportion of correct pretest words, while intelligibility improvement scores were calculated by subtracting this proportion from the proportion of correct posttest words.
Results:
Rhythm perception scores predicted intelligibility improvement scores but not initial intelligibility. On the other hand, receptive vocabulary scores predicted initial intelligibility scores but not intelligibility improvement.
Conclusions:
Expertise in rhythm perception appears to provide an advantage for processing dysrhythmic speech, but a familiarization experience is required for the advantage to be realized. Findings are discussed in relation to the role of rhythm in speech processing and shed light on processing models that consider the consequence of rhythm abnormalities in dysarthria.
OBJECTIVES: Our aim with this article is to evaluate whether the prevalence of hearing loss is increasing among adolescents living in the United States.
METHODS: All available data about hearing loss among adolescents from the large, federally funded National Health and Nutrition Examination Survey (NHANES) were analyzed. By using the 4 data releases between 1994 and 2010 (a total of 6891 adolescents), the prevalence of adolescent hearing loss >15 and ≥25 dB at low frequencies (0.5, 1, and 2 kHz) and high frequencies (3, 4, 6, and 8 kHz) for bilateral, unilateral, and any loss were calculated.
RESULTS: Only 13 of 90 comparisons of prevalence across combinations of degree, frequency, and laterality of hearing loss revealed a statistically significant increase at P < .05. Among the 18 subgroups of degree, frequency, and laterality, 61% had a lower prevalence of hearing loss in 2010 than in 1994, and 100% of the subgroups had a lower prevalence in 2010 than in 2006.
CONCLUSIONS: With previous analyses of NHANES data from 1994 to 2006, researchers showed that hearing loss among US adolescents was increasing. Based on the NHANES data from 1994 to 2010 that are now available, there is no consistent evidence that hearing loss among adolescents in the United States is increasing. Results reveal that conclusions about trends using data from 2 time points can be misleading. NHANES should resume collecting audiometric data as part of their data collection protocol so that trends in the prevalence of childhood hearing loss can be documented.
Background:
The effects of sexual trauma on long-term health care utilization and costs are not well understood due to infrequent documentation of sexual trauma history in health care systems. The Veteran's Health Administration provides a unique opportunity to address this constraint as sexual trauma is actively screened for as part of routine care.
Methods:
We used a retrospective cohort design to analyze Veteran's Health Administration mental health and medical service utilization and costs as a function of a positive screen for exposure to military sexual trauma (MST) among Veterans of recent conflicts in Iraq and Afghanistan. We computed adjusted 5-year estimates of overall utilization and costs, and utilization and costs determined not to be related to MST.
Results:
The cohort included 426,223 men and 59,611 women. A positive MST screen was associated with 50% higher health care utilization and costs relative to a negative screen. Overall, a positive relative to negative MST screen was associated with a 5-year incremental difference of 34.6 encounters and $10,734 among women, and 33.5 encounters and $11,484 among men. After accounting for MST-related treatment, positive MST screen was associated with 11.9 encounters and $4803 among women, and 19.5 encounters and $8001 among men.
Conclusions:
Results demonstrate significant and consistent differences in health care utilization and costs between Veterans with a positive relative to negative MST screen. Even after accounting for MST-related care, a positive screen was associated with significantly higher utilization and costs. MST-related needs may be more readily recognized in women relative to men.
This study replicated, with modifications, previous research of dyad reading using texts at various levels of difficulty (Morgan, 1997). The current project measured the effects of using above–grade-level texts on reading achievement and sought to determine the influences of dyad reading on both lead and assisted readers. Results indicate that weaker readers, using texts at two, three, and four grade levels above their instructional levels with the assistance of lead readers, outscored both proficient and less proficient students in the control group across multiple measures of reading achievement. However, the gains made by assisted readers were not significantly different relative to the various text levels. When all assessments were considered, assisted readers reading texts two grade levels above their instructional levels showed the most robust gains in oral reading fluency and comprehension. Lead readers also benefited from dyad reading and continued their respective reading developmental trajectories across measures.
Exploratory mediation analysis refers to a class of methods used to identify a set of potential mediators of a process of interest. Despite its exploratory nature, conventional approaches are rooted in confirmatory traditions, and as such have limitations in exploratory contexts. We propose a two-stage approach called exploratory mediation analysis via regularization (XMed) to better address these concerns. We demonstrate that this approach is able to correctly identify mediators more often than conventional approaches and that its estimates are unbiased. Finally, this approach is illustrated through an empirical example examining the relationship between college acceptance and enrollment.
Background
Many dynamics in the relationship among military service-related disabilities, health care benefits, mental health disorders, and post-deployment homelessness among US Veterans are not well understood.
Objectives
Determine whether Veterans with a disability-related discharge from military service are at higher risk for homelessness, whether Veterans Health Administration (VHA) service-connected disability benefits mitigates that risk, and whether risks associated with discharge type, service-connected disability, or the interaction between them vary as a function of mental health disorders.
Methods
Retrospective cohort study of 364,997 Veterans with a disability-related or routine discharge and initial VHA encounter between 2005–2013. Logistic regression and survival analyses were used to estimate homelessness risk as a function of discharge status, mental health disorders, and receipt of VHA disability benefits.
Results
Disability-discharged Veterans had higher rates of homelessness compared to routine discharges (15.1 verses 9.1 per 1,000 person-years at risk). At the time of the first VHA encounter, mental health disorders were associated with differentially greater risk for homelessness among Veterans with a disability discharge relative to those with a routine discharge. During the first year of VHA service usage, higher levels of disability benefits were protective against homelessness among routinely-discharged Veterans, but not among disability-discharged Veterans. By 5-years, disability discharge was a risk factor for homelessness (AOR=1.30).
Conclusions
In the long-term, disability discharge is an independent risk factor for homelessness. While VHA disability benefits help mitigate homelessness risk among routinely-discharged Veterans during the early reintegration period, they may not offer sufficient protection for disability-discharged Veterans.
Objective:
The coevolution of adolescent social networks, alcohol use, and physical activity is studied. Previous research has independently evaluated each behavior, overlooking the potential power of examining their development within a shared social context. The current study extends previous research by examining the dynamics of friendship networks, alcohol use, and physical activity in conjunction, including the concurrent engagement in both behaviors, with a nationally representative sample of U.S. adolescents. Special attention is paid to differing patterns of peer selection and peer assimilation across behaviors.
Method:
Data come from 2 high schools (n = 640; n = 1,156) within the National Longitudinal Study of Adolescent to Adult Health. Longitudinal stochastic actor-based models were used to separate peer selection and assimilation processes to differentiate the mechanisms linking friendships and both behaviors as well as the relationship between alcohol use and physical activity.
Results:
Findings suggest distinct differences in the importance of peer selection and assimilation processes to adolescent alcohol use and physical activity. In both schools, adolescents selected friends based on similarity in alcohol use, but no selection effect was found for physical activity. Conversely, assimilation to friends' behavior occurred for physical activity, yet evidence for alcohol assimilation was mixed. No significant relationship between alcohol use and physical activity emerged.
Conclusions:
Intervention efforts that focus on friend influence in changing health behavior may have particular success with adolescent physical activity. Programs aimed at alcohol use would benefit from including an emphasis on preventing negative friend formations. (PsycINFO Database Record
Measurement error adds noise to predictions, increases uncertainty in parameter estimates, and makes it more difficult to discover new phenomena or to distinguish among competing theories. A common view is that any study finding an effect under noisy conditions provides evidence that the underlying effect is particularly strong and robust. Yet, statistical significance conveys very little information when measurements are noisy. In noisy research settings, poor measurement can contribute to exaggerated estimates of effect size. This problem and related misunderstandings are key components in a feedback loop that perpetuates the replication crisis in science.