abstract: Statistical mediation analysis allows researchers to identify the most important the mediating constructs in the causal process studied. Information about the mediating processes can be used to make interventions more powerful by enhancing successful program components and by not implementing components that did not significantly change the outcome. Identifying mediators is especially relevant when the hypothesized mediating construct consists of multiple related facets. The general definition of the construct and its facets might relate differently to external criteria. However, current methods do not allow researchers to study the relationships between general and specific aspects of a construct to an external criterion simultaneously. This study proposes a bifactor measurement model for the mediating construct as a way to represent the general aspect and specific facets of a construct simultaneously. Monte Carlo simulation results are presented to help to determine under what conditions researchers can detect the mediated effect when one of the facets of the mediating construct is the true mediator, but the mediator is treated as unidimensional. Results indicate that parameter bias and detection of the mediated effect depends on the facet variance represented in the mediation model. This study contributes to the largely unexplored area of measurement issues in statistical mediation analysis. / Dissertation/Thesis / Masters Thesis Psychology 2016

abstract: Relational turbulence theory (RTT) has primarily explored the effects of relational uncertainty and partner interdependence on relational outcomes. While robust, the theory fails to account for uncertainties and perceived interdependence stemming from extra-dyadic factors (such as partners’ social networks). Thus, this dissertation had two primary goals. First, scales indexing measures of social network-based relational uncertainty (i.e., network uncertainty) and social network interdependence are tested for convergent and divergent validity. Second, measurements of network uncertainty and interdependence are tested alongside measures featured in RTT to explore predictive validity. Results confirmed both measurements and demonstrated numerous significant relationships for turbulence variables. Discussions of theoretical applications and future directions are offered. / Dissertation/Thesis / Doctoral Dissertation Communication Studies 2018

Submitted by Leonardo Freitas (leonardo.hfreitas@ufpe.br) on 2015-04-10T14:27:21Z No. of bitstreams: 2 Tese Marcos Gabriel F Mendes.pdf: 1549891 bytes, checksum: 54640abf22622a7da0d29005cfc63db6 (MD5) license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) / Made available in DSpace on 2015-04-10T14:27:22Z (GMT). No. of bitstreams: 2 Tese Marcos Gabriel F Mendes.pdf: 1549891 bytes, checksum: 54640abf22622a7da0d29005cfc63db6 (MD5) license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) Previous issue date: 2013 / PPGBV; FACEPE; CNPq; / Entender como a Diversidade Funcional (DF) de assembleias de organismos afeta a complexidade estrutural do habitat em paisagens fragmentadas é um passo fundamental para se avaliar o funcionamento adequado do ecossistema e qual valor de conservação desses ambientes modificados pelo homem. Utilizando a DF obtida através de um conjunto de oito atributos funcionais descritos para 1985 indivíduos da assembleia de árvores em 19 comunidades, comparamos dois modelos causais distintos entre a DF e quatro variáveis de complexidade estrutural (produção de serrapilheira, índice de área foliar, área basal e luz transmitida difusa) em dois tipos de habitats: (i) fragmentos florestais < 100 ha e (ii) áreas de floresta primária (controle). Os resultados mostram que a DF afeta estruturalmente o habitat, principalmente no que se refere à produção de serrapilheira e variação da área basal florestal, em grandes segmentos de floresta. Por outro lado, a relação entre DF e complexidade estrutural em fragmentos < 100 ha é inexistente, sugerindo que a estruturação do habitat dependa basicamente do estágio sucessional e pressões provenientes da matriz, as quais os fragmentos são submetidos. Este estudo reforça a importância da DF sobre a estruturação do habitat, mostrando que esta relação em pequenos fragmentos está sujeita à distorções resultantes dos efeitos da frequência relativa de determinadas estratégias de vida favorecidas pela modificação da paisagem e da maior sensibilidade desses habitats aos efeitos físicos provenientes da matriz.

Submitted by Leonardo Freitas (leonardo.hfreitas@ufpe.br) on 2015-04-10T17:22:05Z No. of bitstreams: 2 Tese Marcos Gabriel F Mendes 2013 (PPGBV_UFPE).pdf: 1549891 bytes, checksum: 54640abf22622a7da0d29005cfc63db6 (MD5) license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) / Made available in DSpace on 2015-04-10T17:22:05Z (GMT). No. of bitstreams: 2 Tese Marcos Gabriel F Mendes 2013 (PPGBV_UFPE).pdf: 1549891 bytes, checksum: 54640abf22622a7da0d29005cfc63db6 (MD5) license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) Previous issue date: 2003 / PPGBV; CEPAN; FACEPE; CNPq / Entender como a Diversidade Funcional (DF) de assembleias de organismos afeta a complexidade estrutural do habitat em paisagens fragmentadas é um passo fundamental para se avaliar o funcionamento adequado do ecossistema e qual valor de conservação desses ambientes modificados pelo homem. Utilizando a DF obtida através de um conjunto de oito atributos funcionais descritos para 1985 indivíduos da assembleia de árvores em 19 comunidades, comparamos dois modelos causais distintos entre a DF e quatro variáveis de complexidade estrutural (produção de serrapilheira, índice de área foliar, área basal e luz transmitida difusa) em dois tipos de habitats: (i) fragmentos florestais < 100 ha e (ii) áreas de floresta primária (controle). Os resultados mostram que a DF afeta estruturalmente o habitat, principalmente no que se refere à produção de serrapilheira e variação da área basal florestal, em grandes segmentos de floresta. Por outro lado, a relação entre DF e complexidade estrutural em fragmentos < 100 ha é inexistente, sugerindo que a estruturação do habitat dependa basicamente do estágio sucessional e pressões provenientes da matriz, as quais os fragmentos são submetidos. Este estudo reforça a importância da DF sobre a estruturação do habitat, mostrando que esta relação em pequenos fragmentos está sujeita à distorções resultantes dos efeitos da frequência relativa de determinadas estratégias de vida favorecidas pela modificação da paisagem e da maior sensibilidade desses habitats aos efeitos físicos provenientes da matriz

The mediation analysis has been used to test if the effect of one variable on another variable is mediated by the third variable. The mediation analysis answers a question of how a predictor influences an outcome variable. Such information helps to gain understanding of mechanism underlying the variation of the outcome. When the mediation analysis is conducted on hierarchical data, the structure of data needs to be taken into account. Krull and MacKinnon (1999) recommended using Multilevel Modeling (MLM) with nested data and showed that the MLM approach has more power and flexibility over the standard Ordinary Least Squares (OLS) approach in multilevel data. However the MLM mediation model still has some limitations such as incapability of analyzing outcome variables measured at the upper level. Preacher, Zyphur, and Zhang (2010) proposed that the Multilevel Structural Equation Modeling (MSEM) will overcome the limitation of MLM approach in multilevel mediation analysis. The purpose of this study was to examine the performance of the MSEM approach on non-normal hierarchical data. This study also aimed to compare the MSEM method with the MLM method proposed by MacKinnon (2008) and Zhang, Zyphur, and Preacher (2009). The study focused on the null hypothesis testing which were presented by Type I error, statistical power, and convergence rate. Using Monte Carlo method, this study systematically investigates the effect of several factors on the performance of the MSEM and MLM methods. Designed factors considered were: the magnitude of the population indirect effect, the population distribution shape, sample size at level 1 and level 2, and the intra-class correlation (ICC) level. The results of this study showed no significant effect of the degree of non-normality on any performance criteria of either MSEM or MLM models. While the Type I error rates of the MLM model reached the expected alpha level as the group number was 300 or higher, the MSEM model showed very conservative performance in term of controlling for the Type I error with the rejection rates of null conditions were zero or closed to zero across all conditions. It was evident that the MLM model outperformed the MSEM model in term of power for most simulated conditions. Among the simulation factors examined in this dissertation, the mediation effect size emerged as the most important one since it is highly associated with each of the considered performance criteria. This study also supported the finding of previous studies (Preacher, Zhang, & Zyphur, 2011; Zhang, 2005) about the relationship between sample size, especially the number of group, and the performance of either the MLM or MSEM models. The accuracy and precision of the MLM and MSEM methods were also investigated partially in this study in term of relative bias and confidence interval (CI) width. The MSEM model outperformed the MLM model in term of relative bias while the MLM model had better CI width than the MSEM model. Sample size, effect size, and ICC value were the factors that significantly associate with the performance of these methods in term of relative bias and CI width.

Abstract The fundamental choice among governance mechanism is whether to externally organize transactions outside the boundary of the firm in the market, or whether to internally organize transactions within the firm's boundaries. In other words, major decision which is made on the firm's organizational strategy culminates in the make-or-buy decisions. In business and especially in the context of logistics, the worldwide usage and importance of outsourcing has grown dramatically over the last decades and researchers have reported on the outsourcing of logistics functions from several perspectives and a growing interest towards outsourcing is indicated by the volume of writings on the subject in scholarly journals, trade publications and popular magazines. The theoretical framework in outsourcing studies has commonly been the theory of the firm in microeconomics, transaction cost theory, agency theory, marketing or strategic management. However, according to recent studies it seems that several perspectives are needed when studying the development of relationships and the antecedents that underlie outsourcing decisions. Hence, in this study, concepts will be used from several theoretical backgrounds to get an eclectic view of outsourcing. The main research question is to study how the buyers' logistics outsourcing decisions contribute to the accomplishment of goals in business networks. Empirical part of thesis contains two data sets. First data were collected in November 2005 and the target group in this data was northern Finnish companies. Totally 161 acceptable responses were received, corresponding to a 27.4 percent response rate. The second data were collected from industrial companies in Finland during spring 2008. In the second data, 235 acceptable responses were returned, representing a response rate of 22.5 percent. As a result, a two dimensional model was created for describing outsourcing relationships in the logistics service markets. On the one hand, network economies can be gained through horizontal mode of outsourcing, where focus is in unit costs of services and the way to achieve lowest possible unit costs are short-term bidding games among service providers. On the other hand, network economies can be achieved through vertical mode of outsourcing with cooperation and strategic partnership where all participants concentrate on their core competences and thus create network economies through transactional value in long-term. In the middle are hybrid modes of outsourcing where focus is on both unit costs of services and transaction costs. These outsourcing modes are where the outsourcing strategies arise and in this way, the thesis contributes to theoretical development of outsourcing phenomenon and concepts behind logistics outsourcing decision making.

Recently there has been a renewed interest in formative measurement and its role in properly specified models. Formative measurement models are difficult to identify, and hence to estimate and test. Existing solutions to the identification problem are shown to not adequately represent the formative constructs of interest. We propose a new two-step approach to operationalize a formatively measured construct that allows a closely matched common factor equivalent to be included in any structural equation model. We provide an artificial example and an original empirical study of privacy to illustrate our approach. Detailed proofs are given in an appendix.

The World Health Organization and the leading hospice organizations have emphasized the inclusion of family caregivers of hospice patients with cancer into end-of-life care, as these two dyad members may spiritually and emotionally influence each other. Given that depression and spiritual needs, which are prominent in these pairs, may impair quality of life (QOL) of hospice dyads, examining mutuality within dyads is imperative to develop a more accurate model that includes family caregivers. Therefore, the purpose of the study was to elucidate the importance of mutual effects within hospice dyads by examining the contribution of depression and unmet spiritual needs on their personal and their counterparts’ QOL. Structural equation modeling was used to integrate the feature of actor and partner effects in the Actor-Partner Interdependence Model. After eliminating outliers, the final sample was comprised of 660 hospice dyads in which the majority of hospice patients were white (97%) and male (56.6%) with a mean age of 73 years. Most of the family caregivers were white (95.9%) and female (73.5%) with a mean age of 65 years. On average, hospice patients reported a depression score of 4.00 (SD = 1.53), and their family caregivers had a significantly lower mean depression score of 3.65 (SD = 1.48). With respect to their spiritual needs, 25.5% of hospice patients indicated going to religious services was an unmet need, and about 13% of family caregivers also reported that going to religious services was an unmet spiritual need, followed by being with friends, laughing, thinking happy thoughts, and being around children. The results of structural equation modeling revealed that depression and spiritual needs in cancer patients and family caregivers exhibited significant actor effects on the individual’s QOL after controlling for the partner effects. Among the spousal pairs, depression in family caregivers exhibited a positive partner effect on hospice patients’ functional well-being (β = .15, p < .05), implying that as depressive symptoms increase, hospice patients’ functional well-being increases. This study supported the need for considering both as one unit and the mutuality inherent in dyads. The findings of the study suggest the importance of consistent assessment in emotional and spiritual well-being for hospice patients as well as family caregivers, as their concerns may be transmitted to each other due to mutuality existing within the dyads.

The current thesis presents five studies which consider the structure of normal range human personality as measured by psychometric inventories. The primary aim of the thesis was to develop a hierarchical model of the structure of human personality, which not only encapsulated the content of extant personality inventories, but extended the extant models to better represent the accumulated knowledge in the field of personality research. To do so, the thesis reports on the largest item level exploratory and confirmatory factor analytic investigation of the structure of personality to date. In Study 1, the utility of confirmatory factor analysis (CFA) for the investigation of personality structure was established by conducting dimensionality, structural and invariance analysis of the 16 Personality Factor Questionnaire, Version 5, using the US Standardization sample. The results clearly demonstrated that confirmatory models of personality inventories can display model fit, and that structures can be identified which are invariant across samples. In Study 2, 1,772 items from the Eugene-Springfield community sample were used to locate 78 unidimensional narrow personality facets, which were both substantively consistent and displayed strong psychometric properties. These 78 facets were then used to identify a second order 11 factor global structure to human personality, the 11+ Model. The 11+ Model was robust over different rotational criteria, and displayed excellent theoretical coverage of the personality sphere. However, confirmatory factor analyses of the 11 factor solution failed to demonstrate model fit. As a result, three further studies were conducted to explore the possible reasons for model misfit. In Study 3, the model fit of the new exploratory 11 factor solution was considered against model fit for extant structures and inventories. The results showed that across modelling strategy, the fit of newly identified structure was comparable to the extant inventories. In Study 4, the claim the model misfit is caused by the inherent complexity in personality was considered through an application of exploratory structural equation modelling (ESEM). ESEM has been argued to more adequately represent such complexity. Results suggested that the ESEM framework fails to offer additional information to help resolve the substantive problems in personality research. Finally, in Study 5, the sample size required to reliably estimate single factor confirmatory models, and second order structural models, was investigated using Monte Carlo simulations. The results suggest that samples of over 2000 are required to reliably estimate second order structural parameters in confirmatory factor analytic models. This finding suggests the samples used in much published research to investigate confirmatory structural models of personality inventories may be deficient.

Among-individual variation in resource use is pervasive and may have ecosystem-wide effects. This variation between individuals can affect population niche breadth. My study determined if niche breadth was best explained by dispersal of individuals from locations with different prey resources driven by ecosystem level disturbance regimes or competition among individuals inhabiting a site, resulting in dietary partitioning. I used structural equation modeling to examine the direct and indirect effects of several environmental variables spanning gradients of disturbance, competition strength, and food availability on niche breadth of the Eastern Mosquitofish (Gambusia holbrooki). I evaluated two complementary models 1) allowing for only direct effects of disturbance on niche breadth and 2) limiting effects of disturbance on niche breadth to indirect effects via food availability and competitor densities. The partitioning hypothesis excluding direct effects of disturbance on niche breadth was best supported by my data.