Made available in DSpace on 2016-06-02T20:06:04Z (GMT). No. of bitstreams: 1 3437.pdf: 1348932 bytes, checksum: d4b8cd2d1775831eeea609373f32648d (MD5) Previous issue date: 2011-02-11 / Universidade Federal de Minas Gerais / Several authors have preferred to model survival data in the presence of covariates through the hazard function, a fact related to its interpretation. The hazard function describes as the instantaneous average of failure changes over time. In this context, one of the most used models is the Cox s model (1972), in which the basic supposition for its use is that the ratio of the failure rates, of any two individuals, are proportional. However, experiments show that there are survival data which can not be accommodated by the Cox s model. This fact has been determinant in the developing of several types of non-proporcional hazard models. Among them we mention the accelerated failure model (Prentice, 1978), the hybrid hazard model (Etezadi-Amoli and Ciampi, 1987) and the extended hybrid hazard models (Louzada-Neto, 1997 and 1999). Mackenzie (1996) proposed a parametric family of non-proportional hazard model called generalized time-dependent logistic model - GTDL. This model is based on the generalization of the standard logistic function for the time-dependent form and is motivated in part by considering the timeeffect in its setting and, in part by the need to consider parametric structure. The frailty model (Vaupel et al., 1979, Tomazella, 2003, Tomazella et al., 2004) is characterized by the use of a random effect, ie, an unobservable random variable, which represents information that or could not or were not collected, such as, environmental and genetics factors, or yet information that, for some reason, were not considered in the planning. The frailty variable is introduced in the modeling of the hazard function, with the objective of control the unobservable heterogeneity of the units under study, including the dependence of the units that share the same hazard factors. In this work we considered an extension of the GTDL model using the frailty model as an alternative to model data which does not have a proportional hazard structure. From a classical perspective, we did a simulation study and an application with real data. We also used a Bayesian approach to a real data set. / Vários autores têm preferido modelar dados de sobrevivência na presença de covariáveis por meio da função de risco, fato este relacionado à sua interpretação. A função de risco descreve como a taxa instantânea de falha se modifica com o passar do tempo. Neste contexto, um dos modelos mais utilizados é o modelo de Cox (1972) sendo que a suposição básica para o seu uso é que a razão das taxas de falhas, de dois quaisquer indivíduos, sejam proporcionais. Contudo, experiências mostram que existem dados de sobrevivência que não podem ser acomodados pelo modelos de Cox. Este fato tem sido determinante no desenvolvimento de vários tipos de modelos de risco não proporcional. Entre eles podemos citar o modelo de falha acelerado (Prentice, 1978), o modelo de risco híbrido (Etezadi-Amoli e Ciampi, 1987) e os modelos de risco híbrido estendido (Louzada- Neto, 1997 e 1999). Mackenzie (1996) propôs uma nova família paramétrica de modelo de risco não proporcional intitulado modelo de risco logístico generalizado dependente do tempo (Generalized time-dependent logistic model-GTDL). Este modelo é baseado na generalização da função logística padrão para a forma dependente do tempo e é motivado em parte por considerar o efeito do tempo em seu ajuste e, em parte pela necessidade de considerar estrutura paramétrica. O modelo de fragilidade (Vaupel et al., 1979, Tomazella, 2003, Tomazella et al., 2004) é caracterizado pela utilização de um efeito aleatório, ou seja, de uma variável aleatória não observável, que representa as informações que não podem ou não foram observadas, como por exemplo, fatores ambientais e genéticos, ou ainda informações que, por algum motivo, não foram consideradas no planejamento. A variável de fragilidade é introduzida na modelagem da função de risco, com o objetivo de controlar a heterogeneidade não observável das unidades em estudo, inclusive a dependência das unidades que compartilham os mesmos fatores de risco. Neste trabalho consideramos uma extensão do modelo GTDL utilizando o modelo de fragilidade como uma alternativa para ii modelar dados que não tem uma estrutura de risco proporcional. Sob uma perspectiva Clássica, fizemos um estudo de simulação e uma aplicação com dados reais. Também utilizamos a abordagem Bayesiana para um conjunto de dados reais.

近年來，在中國大陸市場有大量公司進行掛牌上市的同時，也有越來越多的公司出現債務逾期甚至是違約的情況。考慮到目前中國經濟增速放緩，處在轉型發展的複雜階段，銀行信貸等資金供應鏈需要謹慎評估企業出現財務困境的風險。但是我們發現金融機構在平常管理信貸業務的時候會盲目地看重高額利潤的回報而忽略借款者潛在的財務危機，而且投資人在進行投資分析的時候往往也會忽略企業的財務狀況而使自己遭受損失，因此從企業的財務狀況入手對其進行財務困境機率的評估有非常重大的現實意義。 本文通過對企業財務指標進行相關分析以構建公司財務困境機率評估模型。本文選取了不良貸款率最高的製造業作為研究對象，將2015年滬深兩地的124家上市製造業公司的財務資料作為訓練樣本，將2014年120家上市公司的財務資料作為檢驗樣本，將交易所特別處理公司劃分為非正常組公司，其餘為正常組。本文通過篩選得出23個財務指標作為研究變數，引入了 Logistic 模型與 SVM 模型，針對單一模型的預測結果在準確率和穩定性方面不理想的問題引入了基於 Logistic 模型、SVM 模型的組合模型，並用檢驗樣本進行了四個模型的相關實證分析，比較了四個模型之間的準確度。 對四個模型進行實證分析的結果表明：Logistic模型穩健性好、可解釋性強、建模過程簡單易操作，但分類精度略低於 SVM 模型；SVM雖然分類精度高，但缺乏可解釋性和穩定性，且建模過程依賴專家知識和經驗；Logistic -SVM 組合模型則兼具其優點，預測精確度較單一模型均有提高，而且研究發現異態並行結構優於串型結構。通過本文建立的模型可以計算出企業的陷入財務困境的機率，有效評估企業的違約風險，進而為相關金融機構和投資者提供放款或投資的判斷依據。 / At present, more and more companies are listed in the Chinese mainland market. At the same time, more and more companies are frequently at risk of default and overdue. Given the slowdown in China's economic growth and the complex environment of transformation and development, the supply of funds such as bank loans and other capital needs to be cautious, debt default, loan overdue cases are still likely to occur one after another. However, we find that financial institutions blindly value the return of high profits while ignoring the potential financial crisis of borrowers in the normal management of credit business, it is of great significance to start with the financial status of a company to assess the probability of financial distress. This paper builds a company default probability assessment model by analyzing the financial indicators of enterprises. This paper selects the manufacturing industry with the highest NPL as the research object. Taking the financial data of 124 listed manufacturing companies in Shanghai and Shenzhen in 2015 as the training samples, using the financial data of 120 listed companies in 2014 as the test sample, Exchange special treatment companies divided into non-normal group companies, the rest for the normal group. According to the data of its 2015 financial indicators, 23 financial indicators were screened out as research variables, and a comprehensive analysis was carried out. The Logistic model and SVM model were introduced. Combined model was introduced based on the Logistic model and SVM model to solve the problem that the prediction accuracy and stability of the single model were not ideal,. Finally, empirical analysis of the four models is carried out using the sample data of listed companies in 2014, and the accuracy of the four models is compared. The results of empirical analysis of the four models show that Logistic regression model has no strict assumptions on the data, a better stability and interpretation, but the classification accuracy is slightly lower than the SVM model. The SVM model has higher classification accuracy, but the disadvantage is the lack of interpretability and stability, the modeling process depends on expert knowledge and experience. In order to balance the stability of Logistic model and the accuracy of SVM model, this paper introduces a combined model based on Logistic model and SVM model. The analysis shows that the prediction accuracy of combined model is higher than that of single model, the combination of Logistic regression model and SVM model based on Parallel structure has a higher prediction accuracy than Sequential structure. The model established in this paper can calculate the default probability of an enterprise, effectively assess companies’ risk of financial distress, and then provide the judgment basis for the relevant financial institutions and investors to lend or invest.

Climate change implication and rural livelihood capitals remain the major inextricable dimensions of sustainability in this twenty first century globally. As a result, the impact and outcome of climate change on rural livelihood capitals, including economic development cannot be overemphasized in Ngaka Modiri Molema District Municipality of the North West Province of South Africa, where the study took place. It is one of the largest maize production regions in South Africa, where a preponderance of the people in the province obtain their livelihood from agriculture which contributes enormously to the promotion of household’s food security. The study, therefore, investigated the adaptation strategies, awareness of climate change, factors that influenced climate change adaptation in North West Province of South Africa, with the aim of ascertaining the effects of climate change on livelihood capitals among small and emerging maize farmers. Stratified random sampling technique was used to select three hundred and forty-six (346) farmers who were interviewed from the study area, while a pre-tested questionnaire was administered to the maize farmers, aiming at matters related to climate change impact on livelihood and adaptation. Data were analyzed using descriptive statistics while inferential statistical tools employed were Principal Component Analysis, Two-Stage Least Square regression model, Binary Logistic regression model, and Tobit regression model. The results of the study showed that climate change was linked to rural livelihood capitals as climate change awareness, low profit and co-operative finance were statistically significant (p<0.05). The study also established that majority of the rural farmers in the study area were aware of climate change, in which farm size, education, ownership of the farm, information received on climate change, source of climate change information, climate change information through extension services, channel of information received on climate change and support received on climate change were statistically significant (p<0.05). Factors such as farm size, household gender, type of farms, who owns the farm, land acquisition, source of climate change information, support received on climate change, and adaptation barrier were statistically significant (p<0.05) and influenced climate change adaptation in the study area. Conclusively, climate change is entwined with rural livelihood, and the variables that are significant to the study were identified. It was therefore recommended that government intervention, access to information, extension service and support, farmers’ networking, adoption of drought and heat stress tolerant seeds, indigenous knowledge should be improved, practiced and promoted among the rural farmers and the stakeholders involved in the study area. / Agriculture, Animal Health and Human Ecology / D. Phil. (Agriculture)

本研究所使用違約機率（Probability of Default, 以下簡稱PD）的預測方法為Robust Logistic Regression（穩健羅吉斯迴歸），本研究發展且應用這個方法是基於下列兩個觀察：1. 極端值常常出現在橫剖面資料，而且對於實證結果往往有很大地影響，因而極端值必須要被謹慎處理。2. 當使用Logit Model（羅吉斯模型）估計違約率時，卻忽略極端值。試圖不讓資料中的極端值對估計結果產生重大的影響，進而提升預測的準確性，是本研究使用Logit Model並混合Robust Regression（穩健迴歸）的目的所在，而本研究是第一篇使用Robust Logistic Regression來進行PD預測的研究。 變數的選取上，本研究使用Z-SCORE模型中的變數，此外，在考慮公司的營收品質之下，亦針對公司的應收帳款週轉率而對相關變數做了調整。 本研究使用了一些信用風險模型效力驗證的方法來比較模型預測效力的優劣，本研究的實證結果為：針對樣本內資料，使用Robust Logistic Regression對於整個模型的預測效力的確有提升的效果；當營收品質成為模型變數的考量因素後，能讓模型有較高的預測效力。最後，本研究亦提出了一些重要的未來研究建議，以供後續的研究作為參考。 / The method implemented in PD calculation in this study is “Robust Logistic Regression”. We implement this method based on two reasons: 1. In panel data, outliers usually exist and they may seriously influence the empirical results. 2. In Logistic Model, outliers are not taken into consideration. The main purpose of implementing “Robust Logistic Regression” in this study is: eliminate the effects caused by the outliers in the data and improve the predictive ability. This study is the first study to implement “Robust Logistic Regression” in PD calculation. The same variables as those in Z-SCORE model are selected in this study. Furthermore, the quality of the revenue in a company is also considered. Therefore, we adjust the related variables with the company’s accounts receivable turnover ratio. Some validation methodologies for default risk models are used in this study. The empirical results of this study show that: In accordance with the in-sample data, implementing “Robust Logistic Regression” in PD calculation indeed improves the predictive ability. Besides, using the adjusted variables can also improve the predictive ability. In the end of this study, some important suggestions are given for the subsequent studies.

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / This dissertation aims to analyze the items and dimensions of quality related to apartments in the city of Santa Maria / RS. It is underlined that quality investigated comes to compliance with the characteristics required by customers. About the methodological proceedings, 39 characteristics of location qualities, position and typological were listed according to the bibliography and sequentially reviewed by the real estate agencies. Subsequently, on the real estate agencies, data were collected of 500 apartments sold on 04/01/2013 to 08/25/2014; representing 37% of apartments sold in the city in that period. The data analysis began with the classical theory of tests, using Exploratory Factor Analysis and Confirmatory Factor Analysis sequentially, using the varimax rotation; which identified two factors, based on the criterion of Kaiser. Thus, the approach of Item Response Theory was opportunity, with the logistic model of two parameters as well, the presentation of the critical aspects on the use of Item Response Theory. The first model of Item Response Theory, whose latent trait was named quality of apartments about status, are compost of four items; while the second model, the latent trait quality of apartments about utility, no identified items Sequentially, it was found that the analyzed apartments had scores between 80 to 90, thus, it is clear that most of the apartments investigated for status have the score features 80 in ITR. Therefore it is possible conclude that the proposed objective of this dissertation was achieved. / Esta dissertação visa analisar os itens e dimensões da qualidade referentes aos apartamentos da cidade de Santa Maria/RS. Salienta-se que a qualidade estudada se trata da satisfação das características requeridas pelos clientes. Acerca dos procedimentos metodológicos, 39 características acerca de qualidades de localização, posição e tipológicas foram elencados de acordo com a bibliografia e sequencialmente verificados nas agências imobiliárias. Posteriormente, nas agências imobiliárias, foram coletados dados de 500 apartamentos vendidos nos períodos de 04/01/2013 a 25/08/2014; representando 37% dos apartamentos vendidos na cidade no referido período. O tratamento dos dados iniciou com a Teoria Clássica dos Testes, utilizando a Análise Fatorial Exploratória e sequencialmente a Análise Fatorial Confirmatória, utilizando a rotação ortogonal varimax; que apontou dois fatores, tendo como base o critério de Kaiser. Oportunizando assim a abordagem da Teoria de Resposta ao Item, apresentando o Modelo Logístico de dois parâmetros bem como, a apresentação dos aspectos críticos acerca da utilização da Teoria de Resposta ao Item. O primeiro modelo da Teoria de Resposta ao Item, cujo traço latente foi denominado qualidade dos apartamentos quanto ao status do apartamento, é composto por quatro itens; enquanto o segundo modelo, de traço latente qualidade dos apartamentos quanto à utilidade, não gerou itens. Sequencialmente, verificou-se que os apartamentos analisados possuíam escore entre 80 a 90, por conseguinte, é possível afirmar que a maioria dos apartamentos investigados quanto a status possuem as características de escore 80 na TRI. Portanto, é possível afirmar que, o objetivo proposto da presente dissertação foi alcançado.

Diplomová práce pojednává o stabilizaci diskrétního logistického modelu pomocí několika řídících metod. Je zde provedena především stabilizace rovnováh, 2-periodických cyklů a 3-periodických cyklů. Ke stabilizaci systému je využito proporčního zpětně-vazebního řízení, zpětně-vazebního řízení s časovým zpožděním a řízení založeného na predikci. U každé metody je diskutovaná stabilizační množina pro řídící zesilovač spolu s oblastmi stability pro odpovídající kontrolovaná řešení. Všechny teoretické výsledky jsou ilustrovány grafickými interpretacemi v softwaru MATLAB. Podpůrné výpočty jsou provedeny pomocí softwaru Maple.