Handling of clustered or nested data structures requires the use of multilevel modeling techniques. One such multilevel modeling technique is multilevel structural equation modeling (MLSEM). While estimation of indirect effect parameters and standard errors based on the conventional multilevel model (MMM) has been assessed, this is not the case for the use of the MLSEM model for estimating indirect effects. This simulation study was designed to investigate the use of the MLSEM for estimating mediated effects for the “upper-level” mediation model as compared with the MMM. The following conditions were manipulated: number of clusters (G), within-cluster sample size (nj ), intra-class correlation, measurement error in the mediator, and the true value of the mediated effect derived from various patterns of true values for a and b. The generating model entailed an upper-level mediation model for a cluster-randomized trial that included a dichotomous level two independent variable, a cluster-level latent mediator and an individual-level latent dependent variable both with four indicators. Relative parameter and standard error bias, obtained using the MLSEM and the MMM were evaluated and compared. Percent coverage was calculated and compared when PRODCLIN was used to calculate the confidence interval estimates of the ab effect. Finally, Type I error rates for conditions when ab = 0 were assessed and compared. In addition, statistical power for detecting a truly non-zero mediated effect was tallied and compared across models. Results showed that use of the MMM provided inaccurate and misleading parameter and standard error estimates for the estimates of the mediated effect, especially when the true values of a, b and ab were not zero and the measurement error for M was large. However, the MLSEM estimates were also unacceptable in some of the conditions with small values for G and nj. Researchers are encouraged to use the MLSEM for assessing the multilevel mediated effects when either or both paths a and b are expected to be non-zero, if G is at least 40 and nj is also greater than 40. Results are presented and discussed along with implications for applied researchers intending to assess mediated effect with clustered data. / text

Research suggests that living in communities with high densities of persons from their own ethnic group improves the overall health of older Mexican Americans. One hypothesis is that residing in high ethnic density areas allows characteristics of Mexican culture such as strong social ties and social cohesion, to have a beneficial effect. The majority of investigations focused on ethnic density effects, however, have utilized relatively loose interpretations of what constitutes the appropriate social-geographic area to be studied. Moreover it is not clear how certain dimensions of residential segregation are protective or harmful toward health, particularly when measuring ethnic residential segregation from a geographic information systems (GIS) perspective. The effects of ethnic density and segregation have not been directly or quantitatively tested using the kind of multi-level methodology that can effectively capture data from both personal and environmental characteristics. The present study assessed how multiple geographic/neighborhood factors including ethnic density, neighborhood social cohesion, and social ties may serve as resources for health and health service use of older Mexican Americans. The study had three objectives: 1. To examine whether protective/deleterious effects of ethnic density exist when we use the more commonly used approach to measuring ethnic density (proportion of ethnic group within a specific census unit), and whether the ethnic density effect is increased when an alternative measurement approach (proximity weighted density) is used that relies on more than a single, specific census unit . 2. To examine how different dimensions of ethnic segregation are related to perceived social support, number of social ties, and perception of social cohesion in their neighborhood. 3. To examine whether or not social cohesion mediate the relationship between ethnic density or segregation and health status/health service use. The study represents a secondary analysis of data from the fifth interview wave of the Hispanic Established Populations for the Epidemiologic Study (H-EPESE; PI: Markides). Using geographic information systems (GIS), proximity weighted ethnic density and residential segregation indices were calculated, as well as more standard measures of density based on composition of the census tract in which participant lived. Since the H-EPESE dataset has a clustered structure where individuals are nested within neighborhoods, multilevel modeling techniques were employed. Results suggest that the several approaches here employed to measure ethnic composition of the local environment are complementary. First, the proportion of Hispanics in the neighborhood as defined by the use of census tracts, is both simple and the data easily accessible to researchers. This proportion, or what is often called density, was found to associate with several outcome measures in much the same way, and with similar proportions of variance as the more complex ways of method. The latter, however, made significant contributions that often were relatively independent of the census tract based proportions and thus add significantly to our understanding of the role of the ethnic neighborhood. These more complex measures, moreover, may potentially contribute even more: analyses using these newer approaches were limited by the lack of street address or census block data. Access to such data was not possible due to confidentiality issues surrounding the use of highly specific geographic information that could potentially identify the participant. Results did strongly suggest the value of a residential segregation index as a means of demonstrating that the ethnic environment and urban-rural composition of the residential environment contributes to our understanding of the importance of social coherence and social ties. It was found for example that older Mexican Americans who lived in neighborhoods with higher exposure segregation (i.e., neighborhoods where an individual from one particular racial/ethnic group has a higher probability of encountering members of another group, rather than from their own group) have higher depressive symptoms, as measured by the Center for Epidemiologic Studies Depression (CES-D) scale. This relationship was mediated by individual level data on perception of social cohesion. While in all cases causal interpretations were limited by the lack of a true experimental design the results generally do demonstrate the value of the newer, complementary, approaches to assessment of racial/ethnic density.

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

No description available.

No description available.

This study aimed to examine the mediating effect of job satisfaction in the relationship between role ambiguity and organizational citizenship behavior (OCB) according to the “HEalthy and Resilient Organization” model in two local corporations.. A multilevel analysis of mediation was employed to examine the relationship between these variables, controlling for the effect of employee division. The sample consisted of a total of 340 employees. The results indicate that job satisfaction exhibits a total mediation in the relationship between role ambiguity and OCB of public employees. These results indicate the importance of employees’ well-being to decrease negative effects of role ambiguity in publicemployees’ performance. / El objetivo del estudio era examinar el efecto mediador de la satisfacción laboral en la relación entre la ambigüedad de rol y la conducta de ciudadanía organizacional (CCO) en dos corporaciones locales basándonos en el modelo “HEalthy & Resilient Organization” (HERO; Salanova, Llorens, Cifre & Martínez, 2012). Se propuso un modelo de mediación multinivel entre estas variables, controlando el efecto de la pertenencia de los empleados a sus unidades. 340 empleados públicos participaron en la muestra. Los resultados confirman un efecto mediador total de la satisfacción laboral entre la ambigüedad de rol y la CCO. Este resultado tiene importantes implicaciones en el bienestar de los empleados, al reducir los efectos negativos de la ambigüedad de rol en el desempeño de los empleados públicos. / O objetivo do estudo foi examinar o efeito mediador da satisfação no trabalho na relação entre a ambiguidade do papel é o comportamento de cidadania organizacional (CCO) em duas empresas públicas locais, a proposta do estudo esteve baseada no modelo Healthy & Resilient Organization (HERO; Salanova, Llorens, Cifre & Martínez, 2012). Um modelo de mediação multinível entre essas variáveis foi proposto, controlando o efeito de pertencimento dos funcionários nas suas empresas. A amostra foi composta de 340 funcionários públicos. Os resultados confirmam um efeito mediador da satisfação no trabalho entre a ambiguidade de papel e o CCO. Este resultado tem importantes implicações para o bem-estar dos empregados, reduzindo os efeitos negativos da ambiguidade do papel no desempenho dos funcionários públicos.