Abstract Weighted Quantile Sum Regression for Analyzing Correlated Predictors Acting Through a Mediation Pathway on a Biological Outcome By Bhanu M. Evani, Ph.D. A thesis submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy at Virginia Commonwealth University. Virginia Commonwealth University, 2017. Major Director: Robert A. Perera, Asst. Professor, Department of Biostatistics This work examines mediated effects of a set of correlated predictors using the recently developed Weighted Quantile Sum (WQS) regression method. Traditionally, mediation analysis has been conducted using the multiple regression method, first proposed by Baron and Kenny (1986), which has since been advanced by several authors like MacKinnon (2008). Mediation analysis of a highly correlated predictor set is challenging due to the condition of multicollinearity. Weighted Quantile Sum (WQS) regression can be used as an alternative method to analyze the mediated effects, when predictor correlations are high. As part of the WQS method, a weighted quartile sum index (WQSindex) is computed to represent the predictor set as an entity. The predictor variables in classic mediation are then replaced with the WQSindex, allowing for the estimation of the total indirect effect between all the predictors and the outcome. Predictors having a high relative importance in their association with the outcome can be identified by examining the empirical weights for the individual predictors estimated by the WQS regression method. Other constrained optimization methods (e.g. LASSO) focus on reducing dimensionality of the correlated predictors to reduce multicollinearity. WQS regression in the context of mediation is studied using Monte Carlo simulation for mediation models with two and three correlated predictors. WQS regression’s performance is compared to the classic OLS multiple regression and the regularized LASSO regression methods. An application of these three methods to the National Health and Nutrition Examination Survey (NHANES) dataset examines the effect of serum concentrations of Polychlorinated Biphenyls (independent variables) on the liver enzyme, alanine aminotransferase ALT (outcome), with chromosomal telomere length as a potential mediator. Keywords: Multicollinearity, Weighted Quantile Sum Regression, Mediation Analysis

This study explored how the structural aspects of a social network (that is, number of social ties, frequency of contact, as well as social participation), along with the functional aspect (social support), relate to mental health. Using data from the baseline questionnaire for the tracking cohort of participants in the Canadian Longitudinal Study on Aging, community-dwelling older adults aged 65-85 years old were studied. Cluster analysis was used to group individuals into different clusters, based on their structural social network characteristics. Six clusters were found, ranging from most socially integrated, to moderately integrated, to socially isolated. Univariate analyses indicated that as level of social integration decreased, individuals fared increasingly worse in terms of their mental health outcomes. Furthermore, a series of mediation analyses showed that social support mediated the relationship between social integration level, and mental health, an effect that was strongest for the most socially isolated individuals. / May 2016

Background: Stroke is the second leading cause of disability and mortality in the U.K., therefore research investigating stroke has been highlighted by the National Stroke Strategy to develop studies which are longitudinal and focus on outcome. A comprehensive systematic review (Study One) was undertaken to investigate the role of psychological factors on stroke recovery. This informed the development of the research study (Study Two). The aim of this study was to investigate the role of psychological and cognitive factors on psychological and physical recovery from acute stroke, in a longitudinal study as directed by the National Stroke Strategy. The current study additionally incorporates cognitive neuropsychological elements along with measures of mood, personality and coping. This is the first study to the authors’ knowledge which has investigated repressive coping and Type D personality with stroke. Method: Longitudinal data collection was conducted in two NHS hospitals, with a clinical sample at Time 1 (0-6 weeks post stroke), followed up at Time 2 (3 months post stroke) and Time 3 (6 months post stroke), in the participants’ homes or in nursing homes. Measures used to test independent variables were: Centre for Epidemiologic Studies Short Depression Scale (CES-D 10), Perceived Stress Scale (PSS), Multidimensional Scale of Perceived Social Support (MPSS), Standard Assessment of Negative Affectivity, Social Inhibition, and Type D Personality (DS 14, Type D personality), Marlowe-Crowne Form B & 6 Item STAI (for repressive coping), 3 item Sense of Coherence (SoC) scale, line bi-section & Bells cancellation task (visual neglect), forward digit span (verbal short term memory), Rivermead Behavioural Memory Test (visual short term memory) and the colour word Stroop test (executive function), along with demographic data, stroke markers and health behaviours. Dependent variables were: Quality of life (measured by the SF-36) and physical recovery (modified Rankin Scale). Results: The main analysis used hierarchical multiple regression analyses and mediation analysis to test a series of hypotheses. Physical recovery outcome was predicted by stroke severity, age, stress, repressive coping, social support and visual neglect at different time points. Depression and visual memory were reported as mediators at Time 2. Quality of life outcome was predicted by stroke severity, age, stress, social support, depression and visual neglect at different time points. Conclusions: The results of this study indicate that psychological factors do have an impact on both physical and psychological outcome from stroke. Stress, repressive coping and visual neglect were the most consistent predictors of outcome. Depression and social support played a smaller role, whereas Type D personality was nonsignificant across analyses.

OBJECTIVES: Despite declining tobacco consumption in the U.S., it remains a public health concern. The aim of this study was to assess the impact of tobacco consumption, different tobacco products and smoking duration on dental caries risk among different populations. METHODS: National Health and Nutrition Examination Survey data were used in an epidemiological cross-sectional study of a representative sample of U.S. civilian non-institutionalized population to investigate the influence of tobacco use and different tobacco products on caries prevalence among adolescents and adults. The outcomes were DMFT and DFT indices. Data from the Dental Longitudinal Study (DLS), a closed-panel prospective cohort study of oral health and aging, was used in longitudinal design to determine if changes in tobacco use status change the risk of developing new caries in adult men. Caries increment was used as an outcome. In addition, a cross-sectional study, using DLS, evaluated the association between smoking duration and caries prevalence, and to determine if it is mediated by unstimulated saliva flow rate. DMFS was used as an outcome. Descriptive and bivariate analyses were conducted on dental caries outcomes by tobacco use status and product consumption. Multiple regression, GEE, and mediation analyses were conducted controlling for confounders. RESULTS: Active tobacco use was significantly associated with dental caries, with the highest caries prevalence compared to passive or non-use among adolescents and adults (P-value <.0001). Among adolescents, passive tobacco users had higher caries prevalence than non-tobacco users. In the DLS, continuous use, quitting and starting/ restarting tobacco use between examinations were all associated with higher caries increments (p-value <0.01). Smoking duration was significantly associated with caries prevalence as long smoking duration (31- 70 years) had on average 14 more DMFS than nonsmokers (p-value= 0.0002) and USFR may partially mediate this relation by about 8.70%. CONCLUSION: Dental caries was significantly associated with active tobacco use among adolescents and adults. Caries prevalence is also high among adolescents passively exposed to tobacco. In adult men, continuous tobacco use was associated with higher caries increments. Long-term smoking was associated with high caries prevalence and this relation could be partially mediated by unstimulated saliva flow rate. / 2019-09-26T00:00:00Z

abstract: Mediation analysis is a statistical approach that examines the effect of a treatment (e.g., prevention program) on an outcome (e.g., substance use) achieved by targeting and changing one or more intervening variables (e.g., peer drug use norms). The increased use of prevention intervention programs with outcomes measured at multiple time points following the intervention requires multilevel modeling techniques to account for clustering in the data. Estimating multilevel mediation models, in which all the variables are measured at individual level (Level 1), poses several challenges to researchers. The first challenge is to conceptualize a multilevel mediation model by clarifying the underlying statistical assumptions and implications of those assumptions on cluster-level (Level-2) covariance structure. A second challenge is that variables measured at Level 1 potentially contain both between- and within-cluster variation making interpretation of multilevel analysis difficult. As a result, multilevel mediation analyses may yield coefficient estimates that are composites of coefficient estimates at different levels if proper centering is not used. This dissertation addresses these two challenges. Study 1 discusses the concept of a correctly specified multilevel mediation model by examining the underlying statistical assumptions and implication of those assumptions on Level-2 covariance structure. Further, Study 1 presents analytical results showing algebraic relationships between the population parameters in a correctly specified multilevel mediation model. Study 2 extends previous work on centering in multilevel mediation analysis. First, different centering methods in multilevel analysis including centering within cluster with the cluster mean as a Level-2 predictor of intercept (CWC2) are discussed. Next, application of the CWC2 strategy to accommodate multilevel mediation models is explained. It is shown that the CWC2 centering strategy separates the between- and within-cluster mediated effects. Next, Study 2 discusses assumptions underlying a correctly specified CWC2 multilevel mediation model and defines between- and within-cluster mediated effects. In addition, analytical results for the algebraic relationships between the population parameters in a CWC2 multilevel mediation model are presented. Finally, Study 2 shows results of a simulation study conducted to verify derived algebraic relationships empirically. / Dissertation/Thesis / Ph.D. Psychology 2010

Diploma thesis "Mediation Analysis in Sociology" deals with mediation analysis and possibilities of its application in sociology, depending on the type of the dependent variable that enters the analysis. In the first case the dependent variable is continuous - in this case the SPSS software and its PROCESS add-on are used to directly analyse the mediation. In the second case the dependent variable that enters the analysis is binary - the PROCESS add-on doesn't allow this option; therefore, the analysis is performed in SPSS software by the set of linear and logistic regressions according to the Baron & Kenny method. Two case studies from the field of sociology, GSS (General Social Survey) and ISSP (International Social Survey Programme), are used in the thesis and the consequences of the transition from continuous dependent variable to binary are examined using the secondary analysis of these data.

Indiana University-Purdue University Indianapolis (IUPUI) / This study aims to examine American Muslim well-being and social capital in the face of Islamophobia. Ecological frameworks and social capital theory were synthesized to provide an approach for research, analysis, and social work practice. A mediation analysis was conducted to test the mediating effect of cognitive social capital on the relationship between structural social capital and distress. The paths of structural social capital, cognitive social capital, and distress were conceptualized using the ecological framework of Berkman and colleagues. Special attention was paid to how experiences of Islamophobic discrimination affect cognitive social capital and distress. Structural social capital was operationalized as the number of active memberships in civic organizations; Cognitive social capital was operationalized as trust in major institutions such as schools and the local police and Distress was operationalized using the Kessler Distress Scale. It was hypothesized that an increase in structural social capital would show a decrease in distress with cognitive social capital mediating the path. Results showed that cognitive social capital mediates the relationship between structural social capital and distress. However, an inconsistent mediation was found where an increase in cognitive social capital shows a decrease in distress, but higher levels of structural social capital show an increase in distress. Lastly, the results of the analysis were interpreted to inform current interventions with the American Muslim community through a social work lens.

The intent of this thesis is to explore the mediating effects of ADHD Inattentive symptoms on domestic parent-child interaction problems and working memory. Inattentive symptoms in children with ADHD are known to cause forgetfulness, slow processing speed, and negative parent-child interactions. Working memory deficits in phonological short term memory and the central executive are also well-established in children with ADHD. However, it is currently unknown to what extent inattentive symptoms are responsible for home behavior problems in conjunction with phonological working memory deficits. The aims are tested using two validated, common clinical questionnaires: The Teacher Report Form and the Home Situations Questionnaire. Additionally, working memory and executive function are tested using a phonological letter-number sequencing task and a visuospatial dot-in-the-box task. Results show that inattentive symptoms mediate the relationship between working memory and parent-child interaction problems. Teacher reports of inattention affect the degree to which the child experiences behavior problems at home, and also affects the phonological working memory system implicated in this behavior. Future directions include using a more diverse sample, investigating a wider range of ADHD symptoms, investigating effects across multiple settings, and exploring possibilities of additional executive functioning mediators.

Unsatisfactory results for the aim of reducing suicide rates have motivated the creation of new models to predict suicide, such as the ideation-to-action framework, which focuses on differentiating those with suicidal ideation and those who attempt suicide. The most recently published theory on the ideation-to-action framework is the Three-Step Theory (3ST). Step 1 proposes that the combination of pain and hopelessness causes suicidal ideation, step 2 proposes that ideation increases when pain and hopelessness surpass connectedness, and step 3 proposes that strong suicidal ideation escalates to action when the person has the capacity to attempt suicide. The theory’s concepts are intentionally conceptualized very broadly. The current study aims to compare the traditional conceptualization measurements of the Three-Step Theory with a broader range of predictors. We aim to test the first two steps of the theory through a mediation model and examine if connectedness serves as a mediator in the relationship between psychological pain and hopelessness in predicting the severity of suicidal ideation. We hypothesized that adding a broader conceptualization of pain (i.e., physical pain) and connectedness (i.e., perceived meaning of life, social pleasure, affective empathy) will better account for the level of suicidal ideation. We also hypothesized that connectedness serves as a mediator in the relationship between psychological pain and hopelessness in predicting suicide ideation severity. Following exclusions and removing missing data, 97 participants were available for analysis. Results showed that one of our novel measurements of connectedness, perceived burdensomeness, mediated the relationship between psychological pain and suicidal ideation severity.

No description available.