No description available.

MSCAGR / Department of Agricultural Economics and Agribusiness / The study was conducted in the Mutale Local Municipality, Vhembe District of South Africa on a proportionally randomly selected sample of 153 smallholder farmers after clustering them into agricultural zones and commodity groupings (vegetables under irrigation, dryland maize and citrus fruit farming). Data were collected through a structured qualitative and quantitative questionnaire that was administered face-to-face to respondents and captured into the SPSS Version 24 computer program. The same program was used to analyse data through cross tabulations and logistic regression modelling. In particular, the study focussed on the impact of socio-economic characteristics, challenges that farmers face and views of extension officers on transforming subsistence farmers towards commercialization. The most critical findings of the study were dominance of women, lower youth participation, poor training and educational achievements, non-membership to agricultural organizations, low income levels and dependence on social grants and lack of credit as factors that could impact on farmers’ transformation process. Farmers’ challenges that could impact on transformation were identified as lack of production inputs, water, access to market and supportive infrastructure such as mechanization. However, the views of extension officers regarding transformation centred mostly around insufficient land holdings, climate change and financial support. In contrast to farmers, extension officers viewed market access as a minor challenge. The study recommended for development of strategies that could increase youth participation in farming such as start-up credit, reduction of dependence on social grants by adopting strategies that could increase productivity and thus income, exposure to funding opportunities through training and increased involvement of institutions of higher learning into smallholder farming activities.

Recently, variable selection in high-dimensional data has attracted much research interest. Classical stepwise subset selection methods are widely used in practice, but when the number of predictors is large these methods are difficult to implement. In these cases, modern regularization methods have become a popular choice as they perform variable selection and parameter estimation simultaneously. However, the estimation procedure becomes more difficult and challenging when the data suffer from outliers or when the assumption of normality is violated such as in the case of heavy-tailed errors. In these cases, quantile regression is the most appropriate method to use. In this thesis we combine these two classical approaches together to produce regularized quantile regression methods. Chapter 2 shows a comparative simulation study of regularized and robust regression methods when the response variable is continuous. In chapter 3, we develop a quantile regression model with a group lasso penalty for binary response data when the predictors have a grouped structure and when the data suffer from outliers. In chapter 4, we extend this method to the case of censored response variables. Numerical examples on simulated and real data are used to evaluate the performance of the proposed methods in comparisons with other existing methods.

A inferência Bayesiana está cada vez mais dependente de algoritmos de simulação estocástica, e sua eficiência está diretamente relacionada à eficiência do algoritmo considerado. Uma prática bastante utilizada é a introdução de variáveis auxiliares para obtenção de formas conhecidas para as distribuições {\\it a posteriori} condicionais completas, as quais facilitam a implementação do amostrador de Gibbs. No entanto, a introdução dessas variáveis pode produzir algoritmos onde os valores simulados são fortemente correlacionados, fato esse que prejudica a convergência. O agrupamento das quantidades desconhecidas em blocos, de tal maneira que seja viável a simulação conjunta destas quantidades, é uma alternativa para redução da autocorrelação, e portanto, ajuda a melhorar a eficiência do procedimento de simulação. Neste trabalho, apresentamos propostas de simulação em blocos no contexto de modelos de regressão binária com o uso de variáveis auxiliares. Três classes de funções de ligação são consideradas: probito, logito e probito-assimétrico. Para as duas primeiras apresentamos e implementamos as propostas de atualização conjunta feitas por Holmes e Held (2006). Para a ligação probito-assimétrico propomos quatro diferentes maneiras de construir os blocos, e comparamos estes algoritmos através de duas medidas de eficiência (distância média Euclidiana entre atualizações e tamanho efetivo da amostra). Concluímos que os algoritmos propostos são mais eficientes que o convencional (sem blocos), sendo que um deles proporcionou ganho superior a 160\\% no tamanho efetivo da amostra. Além disso, discutimos uma etapa bastante importante da modelagem, denominada análise de resíduos. Nesta parte adaptamos e implementamos os resíduos propostos para a ligação probito para os modelos logístico e probito-assimétrico. Finalmente, utilizamos os resíduos propostos para verificar a presença de observações discrepantes em um conjunto de dados simulados. / The Bayesian inference is getting more and more dependent of stochastic simulation algorithms, and its efficiency is directly related with the efficiency of the considered algorithm. The introduction of auxiliary variables is a technique widely used for attainment of the full conditional distributions, which facilitate the implementation of the Gibbs sampling. However, the introduction of these auxiliary variables can produce algorithms with simulated values highly correlated, this fact harms the convergence. The grouping of the unknow quantities in blocks, in such way that the joint simulation of this quantities is possible, is an alternative for reduction of the autocorrelation, and therefore, improves the efficiency of the simulation procedure. In this work, we present proposals of simulation using the Gibbs block sampler in the context of binary response regression models using auxiliary variables. Three class of links are considered: probit, logit and skew-probit. For the two first we present and implement the scheme of joint update proposed by Holmes and Held (2006). For the skew-probit, we consider four different ways to construct the blocks, and compare these algorithms through two measures of efficiency (the average Euclidean update distance between interactions and effective sample size). We conclude that the considered algorithms are more efficient than the conventional (without blocks), where one of these leading to around 160\\% improvement in the effective sample size. Moreover, we discuss one important stage of the modelling, called residual analysis. In this part we adapt and implement residuals considered in the probit model for the logistic and skew-probit models. For a simulated data set we detect the presence of outlier used the residuals proposed here for the different models.

O objetivo desta dissertação é estudar uma família de ligações assimétricas para modelos de regressão binária sob a abordagem bayesiana. Especificamente, apresenta-se a estimação dos parâmetros da família de modelos de regressão binária com funções de ligação potência e reversa de potência considerando o método de estimação Monte Carlo Hamiltoniano, na extensão No-U-Turn Sampler, e o método Metropolis-Hastings dentro de Gibbs. Além disso, estudam-se diferentes medidas de comparação de modelos, incluindo critérios de informação e de avaliação preditiva. Um estudo de simulação foi desenvolvido para estudar a acurácia e eficiência nos parâmetros estimados. Através da análise de dados educacionais, mostra-se que os modelos usando as ligações propostas apresentam melhor ajuste do que os modelos usando ligações tradicionais. / The aim of this dissertation is to study a family of asymmetric link functions for binary regression models under Bayesian approach. Specifically, we present the estimation of parameters of power and reversal power binary regression models considering Hamiltonian Monte Carlo method, on No-U-Turn Sampler extension, and Metropolis-Hastings within Gibbs sampling method. Furthermore, we study a wide variety of model comparison measures, including information criteria and measures of predictive evaluation. A simulation study was conducted in order to research accuracy and efficiency on estimated parameters. Through analysis of educational data we show that models using the proposed link functions perform better fit than models using standard links.

A inferência Bayesiana está cada vez mais dependente de algoritmos de simulação estocástica, e sua eficiência está diretamente relacionada à eficiência do algoritmo considerado. Uma prática bastante utilizada é a introdução de variáveis auxiliares para obtenção de formas conhecidas para as distribuições {\\it a posteriori} condicionais completas, as quais facilitam a implementação do amostrador de Gibbs. No entanto, a introdução dessas variáveis pode produzir algoritmos onde os valores simulados são fortemente correlacionados, fato esse que prejudica a convergência. O agrupamento das quantidades desconhecidas em blocos, de tal maneira que seja viável a simulação conjunta destas quantidades, é uma alternativa para redução da autocorrelação, e portanto, ajuda a melhorar a eficiência do procedimento de simulação. Neste trabalho, apresentamos propostas de simulação em blocos no contexto de modelos de regressão binária com o uso de variáveis auxiliares. Três classes de funções de ligação são consideradas: probito, logito e probito-assimétrico. Para as duas primeiras apresentamos e implementamos as propostas de atualização conjunta feitas por Holmes e Held (2006). Para a ligação probito-assimétrico propomos quatro diferentes maneiras de construir os blocos, e comparamos estes algoritmos através de duas medidas de eficiência (distância média Euclidiana entre atualizações e tamanho efetivo da amostra). Concluímos que os algoritmos propostos são mais eficientes que o convencional (sem blocos), sendo que um deles proporcionou ganho superior a 160\\% no tamanho efetivo da amostra. Além disso, discutimos uma etapa bastante importante da modelagem, denominada análise de resíduos. Nesta parte adaptamos e implementamos os resíduos propostos para a ligação probito para os modelos logístico e probito-assimétrico. Finalmente, utilizamos os resíduos propostos para verificar a presença de observações discrepantes em um conjunto de dados simulados. / The Bayesian inference is getting more and more dependent of stochastic simulation algorithms, and its efficiency is directly related with the efficiency of the considered algorithm. The introduction of auxiliary variables is a technique widely used for attainment of the full conditional distributions, which facilitate the implementation of the Gibbs sampling. However, the introduction of these auxiliary variables can produce algorithms with simulated values highly correlated, this fact harms the convergence. The grouping of the unknow quantities in blocks, in such way that the joint simulation of this quantities is possible, is an alternative for reduction of the autocorrelation, and therefore, improves the efficiency of the simulation procedure. In this work, we present proposals of simulation using the Gibbs block sampler in the context of binary response regression models using auxiliary variables. Three class of links are considered: probit, logit and skew-probit. For the two first we present and implement the scheme of joint update proposed by Holmes and Held (2006). For the skew-probit, we consider four different ways to construct the blocks, and compare these algorithms through two measures of efficiency (the average Euclidean update distance between interactions and effective sample size). We conclude that the considered algorithms are more efficient than the conventional (without blocks), where one of these leading to around 160\\% improvement in the effective sample size. Moreover, we discuss one important stage of the modelling, called residual analysis. In this part we adapt and implement residuals considered in the probit model for the logistic and skew-probit models. For a simulated data set we detect the presence of outlier used the residuals proposed here for the different models.

Although forest properties are known to influence snowpack accumulation and spring runoff, the processes underlying the impacts of forest canopy cover on the input of snowmelt to the catchment remain poorly characterized. In this study I show that throughfall and canopy shading can combine to result in maximal snowpacks in forests of moderate canopy density. Snow depth and density data taken shortly before spring melt in the Jemez Mountains of New Mexico show strong correlation between forest canopy density and snow water equivalent, with maximal snow accumulation in forests with density between 25 and 45%. Forest edges are also shown to be highly influential on local snow depth variability, with shaded open areas holding significantly deeper snow than either unshaded open or deep forest areas. These results are broadly applicable in improving estimates of water resource availability, predicting the ecohydrological implications of vegetation change, and informing integrated water resources management.

O objetivo desta dissertação é estudar uma família de ligações assimétricas para modelos de regressão binária sob a abordagem bayesiana. Especificamente, apresenta-se a estimação dos parâmetros da família de modelos de regressão binária com funções de ligação potência e reversa de potência considerando o método de estimação Monte Carlo Hamiltoniano, na extensão No-U-Turn Sampler, e o método Metropolis-Hastings dentro de Gibbs. Além disso, estudam-se diferentes medidas de comparação de modelos, incluindo critérios de informação e de avaliação preditiva. Um estudo de simulação foi desenvolvido para estudar a acurácia e eficiência nos parâmetros estimados. Através da análise de dados educacionais, mostra-se que os modelos usando as ligações propostas apresentam melhor ajuste do que os modelos usando ligações tradicionais. / The aim of this dissertation is to study a family of asymmetric link functions for binary regression models under Bayesian approach. Specifically, we present the estimation of parameters of power and reversal power binary regression models considering Hamiltonian Monte Carlo method, on No-U-Turn Sampler extension, and Metropolis-Hastings within Gibbs sampling method. Furthermore, we study a wide variety of model comparison measures, including information criteria and measures of predictive evaluation. A simulation study was conducted in order to research accuracy and efficiency on estimated parameters. Through analysis of educational data we show that models using the proposed link functions perform better fit than models using standard links.

Direct marketing problems have been intensively reviewed in the marketing literature recently, such as purchase frequency and time, sales profit, and brand choices. However, modeling the customer response, which is an important issue in direct marketing research, remains a significant challenge. This thesis is an empirical study of predicting customer response to direct marketing and applies a Bayesian approach, including the Bayesian Binary Regression (BBR) and the Hierarchical Bayes (HB). Other classical methods, such as Logistic Regression and Latent Class Analysis (LCA), have been conducted for the purpose of comparison. The results of comparing the performance of all these techniques suggest that the Bayesian methods are more appropriate in predicting direct marketing customer responses. Specifically, when customers are analyzed as a whole group, the Bayesian Binary Regression (BBR) has greater predictive accuracy than Logistic Regression. When we consider customer heterogeneity, the Hierarchical Bayes (HB) models, which use demographic and geographic variables for clustering, do not match the performance of Latent Class Analysis (LCA). Further analyses indicate that when latent variables are used for clustering, the Hierarchical Bayes (HB) approach has the highest predictive accuracy.

Purpose In any organization, the Board of Directors acts as the last line of defense against fraud and abuse. Since 2008, the Internal Revenue Service (IRS) has required nonprofit organizations to publicly disclose any significant asset diversion, defined as theft or unauthorized use of assets, that occurred during the filing year. This research study uses this new disclosure of asset diversion to investigate whether proper board policy oversight and/or governance reduces the likelihood of asset diversion. Understanding how policy and governance impacts a nonprofit organization is critical for managers and practitioners to understand. Organizational management, board members and regulatory agencies (auditors, IRS) all have a responsibility to prevent asset diversion and would benefit from a deeper understanding of where the individual failure points exist from within the organization that create an increased chance of asset diversion. Research Methodology This research study spanned the period between 2014 through 2018 and was comprised of 254 nonprofit organizations. The total sample of organizations that were represented in the IRS data sets consisted of 113,899 separate nonprofit organizations. Organizational data collected from IRS 990 filings across each of the 5 years was first isolated by organizations that experienced asset diversion (n=127) and then matched with an equal number of nonprofit organizations that did not experience asset diversion through random sampling. From the IRS filing data, 18 different variables were then tested against the dependent variable, asset diversion, using logistic binary regression analysis. Findings The findings of this study both reaffirmed certain key aspects of asset diversion in nonprofit organizations as well as introduced new key variables that showed significant correlation with an increase in asset diversion. The findings suggest that there are variables from both board policy oversight and board governance regression analysis that show a significant relationship with asset diversion. More specifically, there were three common variables that showed significance throughout each test: organizational required audit, independent auditors, and improper party transaction with family members of current or former directors and/or officers of the organization. One additional variable, improper party transaction with an entity owned or operated by a current or former officer and/or director, showed significance in four of the five models tested, indicating that there is a strong correlation with increasing asset diversion. Keywords: fraud, asset diversion, nonprofit, binary regression, Board of Directors, IRS 990 filing / Business Administration/Strategic Management