Event history analysis is the most prevalent modeling technique used to model event occurrence with longitudinal data (Cox & Oakes, 1984; Menard, 1991; Singer & Willett, 1993, 2003). An alternative is to model longitudinal data within the SEM framework, known as latent variable growth modeling (McArdle, 1988; Meredith & Tisak, 1990), which can provide a more robust framework. Whether or not a student remains in college presents an appropriate context within which to examine the modeling of event occurrence with longitudinal data. The purpose of the study was to compare event history and latent growth modeling as for predicting change in college student perseverance, with college student persistence literature serving as the framework. Students are defined as having persevered if they have earned hours and the end of the semester rather than if they are enrolled at the beginning of the semester, which is the traditional definition of persistence.The population for the study was the 2001 and 2002 cohorts of first-time, full-time freshmen at a large mid-Atlantic urban research university. Stopouts and transfer students were excluded. Data was analyzed for the first five semesters for each cohort. The results showed that parameter estimates were quite consistent across model type and time frame and were mostly consistent with previous research. No one method outperformed the others in terms of predicting correct classification. Using event history analysis with the structural equation modeling framework, however, appeared to be a very promising alternative to event history analysis with logistic regression since one can model error term and examine the differential effects of predictors at each time period. Finally, while latent growth modeling did not outperform the other methods in predictive classification, the study demonstrated it can be used for event occurrence analysis to test more complex theories.

The purpose of this study was to assess the impact of acquiescence on both positively and negatively worded questions, both when unidimensionality was assumed and when it was not. To accomplish this, undergraduate student responses to a previously validated survey of student engagement were used to compare several models of acquiescence, using a priori goodness-offit statistics as evidence for model fit, in order to develop a model that adequately accounted for acquiescence bias. Using a true experimental design, undergraduate students from a variety of classes at a large, urban university were randomly assigned to one of three versions of the same survey of student engagement (all positively worded items, all negatively worded items, an equal balance of both positively and negatively worded items). Structural equation modeling was used to analyze the results. Although the presence of acquiescence was confirmed for both positively and negatively worded items, it was not consistent by content scale or item polarization. This suggests that there may be an interaction between item polarization and content that may cause acquiescence to be present or absent. The scales that did not show acquiescence on the balanced survey portrayed a split factor loading based upon item polarization. Further, the splitting of factor loadings by item polarization was not due to acquiescence, suggesting that something other than acquiescence is causing the loadings to split. Further research is needed to develop models and/or methods to better assess and control for acquiescence. Although demographic groups were compared by gender and race/ethnicity to assess if different groups acquiesced differently, using multi-group confirmatory factor analysis, many of the models did not converge. The findings of this study were limited by the nature of the sample size. Additional research is needed to determine if acquiescence differs by group membership.

Vicarious traumatisation (VT) has been defined as an experience of change in several domains of personhood including worldview, identity, and beliefs related to major psychological needs. Self-care practice is widely considered essential in sustaining personal and professional well-being, and a lack of appropriate practice can enhance the risk of VT in trainee and newly qualified therapeutic practitioners. Both quantitative and qualitative research suggests that mindfulness practice can have a protective role in the risk of VT for trainees. This study examined the relationship between VT, self-care and mindfulness in a sample of 238 trainee therapists from the UK, Australia, Canada and Ireland. Structural equation modelling was used to test a mediation model with good fit with self-care as predictor variable, mindfulness as mediator, and VT as outcome variable. The hypothesis that when controlling for the effects of mindfulness on VT the effect of self-care on VT is no longer significant could not be confirmed as no mediational effect was present. The hypothesis that predicted a negative association between self-care practice and VT was confirmed with a significant total effect although the direct effect of self-care on VT was not significant. Findings are discussed in relation to previous research involving mindfulness in trainee cohorts. Links are made with neuroscience research to consider underlying mechanisms of mindfulness within the context of VT.

The performance of own-label brands varies enormously across countries, with high penetration in Western countries but limited success in Eastern countries. The common explanations for this state are related to market factors such as the development of big retailer chains or the power balance between retailers and manufacturers. However, the role of culture has been overlooked to explain this situation. This study aims to provide insights into the impact of culture on own-label brands performance. This thesis formulates and tests a conceptual framework linking Hofstede s (1980, 2001) five cultural dimensions (power distance, individualism, masculinity, uncertainty avoidance & long-term orientation) to retail market development (size of the retail market) and own-label brands performance, controlling for three socio-economic variables: GDP per capita, Gini index and Government expenditure. Relevant literature is reviewed in order to develop hypotheses. The conceptual model is then tested upon a sample of 65 countries, utilising data collected via secondary sources and the application of structural equation modelling techniques. The results of this study indicate that three out of five Hofstede s cultural dimensions, power distance, individualism and uncertainty avoidance, have a significant impact on retail market development, which in turn, significantly influences own-label brands performance. Moreover, results show that individualism and long-term orientation have a significant direct impact on own-label brands performance. Past studies on this domain are restricted to one or two cultural dimensions and generally involve a limited number of countries. This research therefore pioneers in investigating the five national cultural dimensions across a high number of nations. The findings are important for retailers and may help them to adapt their own-label strategy according to the culture of the nation they are operating in.

In spite of the wealth of research in IS security, there is very little understanding of what actually makes an IS security program successful within an organization. Success has been treated generally as a separate entity from IS security altogether; a great deal of research has been conducted on the "means to the end", while limited research has been focused on truly understanding what the end actually is. The problem compelling this research is that previous studies within the IS security domain do not adequately consider what factors contribute towards IS security success within the organizational context, and how the factors interact. This study built upon Shannon and Weaver (1949) and Mason (1978) to develop a model for predicting IS security success within an organization. A considerable body of information systems security literature was organized based on their findings. Core dimensions of information system security success were identified and operationalized within a model for predicting success with IS security initiatives. The model was empirically validated in a three-phase approach using survey methodology. First, the survey was tested for validity and reliability using an expert panel and pilot study. Next, the survey was administered to a sample, with the results analyzed using Confirmatory Factor Analysis and Structural Equation Modeling techniques. Initial analysis of the measurement model generated through Confirmatory Factor Analysis showed mixed fit. Factor loadings and average variance extracted calculations resulted in the selection of low performing items for removal; after revision, the revised measurement model showed improved fit for all measures. Structural Equation Modeling analysis was conducted on three structural models with varying levels of mediation. Based on the analysis of fit and comparison indices, the model depicting partial mediation was determined to be the best variation of the IS security success model. This study is the first known instance of an empirically tested IS security success model and should provide many avenues for future study, as well as providing practitioners a fundamental roadmap for success within their organizational IS security programs.

Dissertation submitted to the Department of Psychology, University of the Witwatersrand, in fulfilment of the requirements for the degree of Master of Arts. / The aim of the present study was to develop and evaluate a process model linking stressful environmental change, perceived job insecurity and stress reactions, A review of the literature revealed that stressful changes in the environment are linked to individual stress reactions, Stress theory has also recognised that appraisal of a stressful situation leads to stress reactions, Moreover, the literature has identified job Insecurity as a form of appraisal in that it is an internal event reflecting a transformation of beliefs about what 's happening in the organisation and environment. Job insecurity in turn has been shown to result in various stress reactions in individuals, Based on such research and theorising, a causal model was developed and tested using structural equation modeling techniques, It was assessed whether: stressful environmental change impacted upon stress reactions and job insecurity; job insecurity impacted upon stress reactions; and whether Job insecurity operated as a form of appraisal in mediating the relationship between stressful environmental change and stress reactions, The Independent variable, stressful environmental change, was specified as a common factor of the measured variables, political change, social change and organisational change, The proposed mediator variable, job insecurity, was specified as a common factor of the measured variables perceived threat to total job multiplied by powerlessness, and perceived threat to job features multiplied by powerlessness, The dependent variable, stress reactions, was specified as a common factor of the measured variables psychological distress, job dissatisfaction and reduced organisational commitment. The model was tested empirically using a combined sample of 267 subjects from three organisations, Results indicated that all relationships In the proposed model were confirmed, and that a reasonable fit was demonstrated between the empirical data and the theoretical model. Stressful environmental change was causally related to both stress reactions and Job insecurity, Job Insecurity was causally related to stress reactions, and in addition operated as a partial mediator between stressful environmental change and stress reacdons. Conceptual and methodological reasons for the findings are discussed, as well as some theoretical and practical implications, Limitations in the methodology are identified and future considerations of research are suggested, / AC2017

Visitor expenditure can be affected by different economic, socio-demographic and psychological variables. Previous literature have focused on the use of observed tourists and destination characteristics as explanatory variables to explain visitor expenditure, whereas the use of psychological factors has been underresearched. The present study aims to fill in the gap in the existing literature through the exploration of more extensive use of psychological variables. This is accomplished by the use of structural equation modelling (SEM), a methodological approach which seems not to have been applied before in tourism expenditure econometric models. In econometrics expenditure research, Mortazavi (2018) found satisfaction to be an endogenous regressor of expenditure. Hence, the contribution of our model is that it allows for the relationship between visitor satisfaction and visitor expenditure, and vice versa, to be tested simultaneously. Consequently, under this context we may identify the magnitude of one variable impact on another while at the same time accounting for simultaneous relationship between the two paths. The findings of this study go in hand with previous literature and economic theory which have found a positive relationship between visitor satisfaction and visitor expenditure.

This thesis aims to provide clarity on which factors within an organization positively affect its performance in terms of innovation.  Innovation is seen as a critical component of a company’s strategy in achieving market differentiation and profitability, yet for many, it remains a frustrating pursuit.  This study aims to empirically model the relationship between a firm’s investment in innovation and the effect of this investment on its performance.  The method used is Structural Equation Modeling with data gathered from our online survey of 128 respondents from firms within the EU.  This work addresses two research questions, the first being to confirm that a firm’s innovation performance is influenced by both a commitment to human factors focusing on softer values in combination with strong R&D and technical capability.  Secondly, whether the presence of innovation inhibitors influences this relationship.  The findings showed that a firm’s innovation performance is improved when it prioritizes creating an environment and culture that nurtures innovation only when activated through a strong commitment to technical and R&D excellence, but not without this technical capacity.  Secondly, the introduction of innovation inhibitors reconfirmed the first finding, and the relationship between both the human factors within a company and its technical capability, as well as the relationship between this technical capability and its performance was stronger in their presence.

[pt] Nesta pesquisa procurou-se estimar a qualidade da governança praticada por uma amostra significativa de companhias abertas brasileiras, no período entre 2002 e 2006, e relacioná-la aos indicadores precedentes do valor das companhias, que são o risco e o desempenho, de modo a verificar a existência de relações estatísticas significativas entre estas. Para mensurar a qualidade da governança construiu-se um índice composto por vinte perguntas de respostas binárias. Foram utilizados diversos indicadores para o risco como beta local; o beta obtido com o uso do S&P 500; a volatilidade; o risco idiossincrático, e o custo implícito do capital. Para mensurar o desempenho foram utilizadas as variáveis roa (return on assets); roe (return on equity); ets (a margem ebit-to- sales), e o mts (o indicador de valor market-to-sales). Os resultados conseguidos por meio da aplicação do método das regressões lineares simples e múltiplas, em nível crescente de complexidade, são confirmados com robustez pelos resultados obtidos com o uso do método das equações estruturais, e confirmam as hipóteses iniciais. A investigação da endogeneidade da variável governança sugere que esta variável tem caráter endógeno em relação ao risco e à margem. Porém, o teste de Granger não mostra evidências de relação de causalidade originada das variáveis de risco e desempenho na governança, mas revela indícios de relação originada da governança nas variáveis retromencionadas. Os efeitos da possível endogeneidade não prejudicaram os resultados obtidos por meio das regressões lineares. Também se investigou a relação entre subíndices e as variáveis de risco e desempenho. Os resultados confirmam a influência dos subíndices relacionados com a estrutura de propriedade, a transparência e a atuação da administração da companhia no risco e desempenho das empresas. Não se observou relação estatística significativa entre o subíndice relacionado com a política de relacionamento com o investidor e as variáveis risco e desempenho. Por último, constatou-se que a maior dispersão do capital ordinário; a maior participação do controlador no capital total; menores graus de imobilização; maiores conselhos; menor alavancagem operacional e financeira; menores riscos; maiores margens; adoção de programa de ADR níveis 2 ou 3; maior tempo de experiência societária; maiores patrimônios, e a participação no Nível 2 ou Novo Mercado da Bovespa se relacionam positivamente com a qualidade da governança praticada pelas empresas. / [en] This study estimated the quality of governance practiced by a significant sample of Brazilian publicly traded companies between 2002 and 2006, and related it to risk and performance. An index composed of twenty questions, with all answers in binary form, was constructed to measure the quality of governance. Several indicators were used for risk such as the local beta, the beta obtained with the use of the S & P 500 index, share price volatility, idiosyncratic risk and the implicit cost of capital. Measures of performance were the following variables: return on assets), return on equity, the margin of ebit-to- sales, and the ratio of market value-to-sales). The results obtained through the application of the method of simple and multiple linear regressions, in increasing level of complexity, were confirmed, with robustness, by the results obtained by the use of structural equations, confirming the original hypotheses. The investigation of the endogeneity of the variable for governance suggests that this variable has an endogenous character in relation to the risk and margin. Though the test of Granger shows no evidence of a causal relationship between the variables of risk and performance in governance, it shows signs of a causal relationship caused by governance on the variables of risk and performance. The effects of possible endogeneity do not harm the results obtained using the linear regressions. The relationships between sub-indexes of governance and risk and performance were also investigated. The results confirm the influence of the sub-indexes of governance related to the structure of ownership, transparency and administration of the company on the risk and performance of companies. There was no statistically significant relationship between the sub- index related to the politics of relationships with the investor and the variables risk and performance. Finally, it was found that the greater dispersion of holdings of ordinary shares, the greater investment by the controlling shareholder in total capital, lesser degrees of tangible assets, larger boards of directors, lower operating and financial leverage, lower risk, higher margins, the existence of a ADR level 2 or 3 program, more experience in been a public company, greatest volume of assets, and participation in the Level 2 or Bovespa`s New Market`s correlate positively with the quality of governance practiced by the Brazilian publicly traded companies.

Understanding the causal architecture underlying complex systems biology has a great value in agriculture production for the development of optimal management strategies and selective breeding. So far, most studies in this area use only prior knowledge to propose causal networks and/or do not consider the possible genetic confounding factors on the structure search, which may hide important relationships among phenotypes and also bias the resulting inferred causal network. In this dissertation, we explore many structural learning algorithms and present a new one, called PolyMaGNet (Polygenic traits with Major Genes Network analysis), to search for recursive causal structures involving complex phenotypic traits with polygenic inheritance and also allowing the possibility of major genes affecting the traits. Briefly, a multiple-trait animal mixed model is fitted using a Bayesian approach considering major genes as covariates. Next, posterior samples of the residual covariance matrix are used as input for the Inductive Causation algorithm to search for putative causal structures, which are compared to each other using the Akaike information criterion. The performance of PolyMaGNet was evaluated and compared with another widely used approach in a simulated study considering a QTL mapping population. Results showed that, in the presence of major genes, our method recovered the true skeleton structure as well as the causal directions with a higher rate of true positives. The PolyMaGNet approach was also applied to a real dataset of an F2 Duroc × Pietrain pig resource population to recover the causal structure underlying on carcass, meat quality and chemical composition traits. Results corroborated with the literature regarding the cause-effect relationships between these traits and also provided new insights about phenotypic causal networks and its genetic architectures in complex systems biology. / Compreender a arquitetura causal subjacente à sistemas biológicos complexos é de grande valia na produção agrícola para o desenvolvimento de estratégias de manejo e seleção genética. Até o momento, a maior parte dos estudos neste contexto utiliza apenas conhecimento prévio para propor redes causais e/ou não considera fatores de confundimento genético na busca de estruturas, fato que pode ocultar relações importantes entre os fenótipos e viesar inferências sobre a rede causal. Nesta tese, exploramos alguns algoritmos de aprendizagem de estruturas e apresentamos um novo, chamado PolyMaGNet (do inglês, Polygenic traits with Major Genes Network analysis), para buscar estruturas causais recursivas entre características fenotípicas poligênicas complexas e permitindo, também, a possibilidade de efeitos de genes maiores que as afetam. Resumidamente, um modelo misto de múltiplas características é ajustado usando abordagem Bayesiana considerando os genes maiores como covariáveis no modelo. Em seguida, amostras posteriores da matriz de covariância residual são usadas como entrada para o algoritmo de causação indutiva para pesquisar estruturas causais putativas, as quais são comparadas usando o critério de informação de Akaike. O desempenho do PolyMaGNet foi avaliado e comparado com outra abordagem bastante utilizada por meio de um estudo simulado considerando uma população de mapeamento de QTL. Os resultados mostraram que, na presença de genes maiores, o método PolyMaGNet recuperou a verdadeira estrutura do esqueleto, bem como as direções causais, com uma taxa de efetividade maior. O método é ilustrado também utilizando-se um conjunto de dados reais de uma população de suínos F2 Duroc × Pietrain para recuperar a estrutura causal subjacente à características fenotípicas relacionadas a qualidade da carcaça, carne e composição química. Os resultados corroboraram com a literatura sobre as relações de causa-efeito entre os fenótipos e também forneceram novos conhecimentos sobre a rede fenotípica e sua arquitetura genética.