Os modelos de fragilidade são utilizados para modelar as possíveis associações entre os tempos de sobrevivência. Uma outra alternativa desenvolvida para modelar a dependência entre dados multivariados é o uso dos modelos baseados em funções cópulas. Neste trabalho propusemos dois modelos de sobrevivência derivados das cópulas de Ali- Mikhail-Haq (AMH) e de Frank para modelar a dependência de dados bivariados na presença de covariáveis e observações censuradas. Para fins inferenciais, realizamos uma abordagem bayesiana usando métodos Monte Carlo em Cadeias de Markov (MCMC). Algumas discussões sobre os critérios de seleção de modelos são apresentadas. Com o objetivo de detectar observações influentes utilizamos o método bayesiano de análise de influência de deleção de casos baseado na divergência ψ. Por fim, mostramos a aplicabilidade dos modelos propostos a conjuntos de dados simulados e reais. Apresentamos, também, um novo modelo de sobrevivência bivariado com fração de cura, que leva em consideração três configurações para o mecanismo de ativação latente: ativação aleatória, primeira ativação é última ativação. Aplicamos este modelo a um conjunto de dados de empréstimo de Crédito Direto ao modo do Consumidor (DCC) e comparamos os ajustes por meio dos critérios bayesianos de seleção de modelos para verificar qual dos três modelos melhor se ajustou. Por fim, mostramos nossa proposta futura para a continuação da pesquisa. / The frailty models are used to model the possible associations between survival times. Another alternative developed for modeling the dependence between multivariate data is the use of models based on copulas functions. In this paper we propose two derived survival models of copula of the Ali-Mikhail-Haq (AMH) and of the Frank to model the dependence of bivariate data in the presence of covariates and censored observations. For inferential purposes, we conducted a Bayesian approach using Monte Carlo methods in Markov Chain (MCMC). Some discussions on the model selection criteria were presented. In order to detect influential observations we use the Bayesian method of cases of deletion of influence analysis based on the difference ψ. Finally, we show the applicability of the proposed models to sets of simulated and real data. We present, too, a new survival model with bivariate fraction of healing, which takes into account three settings for the latent activation mechanism: random activation, first activation and final activation. We apply this model to a set of Direct Credit loan data to the Consumer mode (DCC) and compare the settings, through Bayesian criteria for selection of models, which of the three models best fit. Finally, we show our future proposal for further research.

Em estudos longitudinais, repetidas observações de uma mesma variável resposta são coletadas na mesma unidade experimental, em diferentes ocasiões. Como diferentes observações são realizadas na mesma unidade, espera-se que estas sejam correlacionadas, e que exista uma heterogeneidade de variâncias nas diferentes ocasiões. Dados longitudinais multivariados são obtidos quando um conjunto de diferentes variáveis respostas são mensuradas na mesma unidade experimental repetidas vezes ao longo do tempo; nesse caso, além da correlação entre observações realizadas na mesma unidade experimental, deve-se considerar também a correlação entre diferentes variáveis respostas. Uma forma de analisar dados longitudinais bivariados é empregar um modelo misto para cada uma das variáveis respostas e uni-los em um modelo misto bivariado especificando a distribuição conjunta para os efeitos aleatórios. As estimativas dos parâmetros desta distribuição comum podem ser usadas para avaliar a relação entre as diferentes respostas. Para exemplificar a utilização da técnica, foram utilizados dados de armazenamento de leite UAT. Os modelos lineares mistos bivariados foram ajustados por meio do software SAS e a análise gráfica foi realizada por meio do software R. Para seleção dos modelos empregou-se os Critérios de Informação de Akaike (AIC) e Bayesiano (BIC), e o teste da razão de verossimilhanças para comparação de modelos encaixados. A utilização do modelo linear misto bivariado permitiu modelar a heterogeneidade de variâncias entre ocasiões e a correlação entre diferentes medidas na mesma unidade experimental, bem como a correlação entre as variáveis respostas. / In longitudinal studies, repeated measurements of a response variable are taken in the same experimental unit over time. . Since different observations are measured on the same experimental unit, it is expected that there is correlation among the repeated measurements and heterogeneity of variances in different occasions. Multivariate Longitudinal Data are obtained when we measure a number of different response variables in the same experimental unit repeatedly over time; in this case, we should also observe a correlation between the different response variables. One way to analyze bivariate longitudinal data is to use a mixed model for each of the response variables, and unite them in bivariate mixed models specifying the joint distribution for random effects. Parameter estimates of this common distribution may be used to evaluate the relationship between different responses. As an example of the use of the technique, UHT milk storage data were used. Models were fitted using SAS software and the graphical analysis was done with software R. To model selection, Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) were used, and maximum likelihood ratio test was used to compare nested models. The use of bivariate mixed linear model allowed to model the heteroscedasticity of the occasions, the correlation between the different measurements in the same experimental unit and also the correlation between the different response variables.

A class of lifetime distributions which has received considerable attention in modelling and analysis of lifetime data is the class of lifetime distributions with bath-tub shaped failure rate functions because of their extensive applications. The purpose of this thesis was to introduce a new class of bivariate lifetime distributions with bath-tub shaped failure rates (BTFRFs). In this research, first we reviewed univariate lifetime distributions with bath-tub shaped failure rates, and several multivariate extensions of a univariate failure rate function. Then we introduced a new class of bivariate distributions with bath-tub shaped failure rates (hazard gradients). Specifically, the new class of bivariate lifetime distributions were developed using the method of Morgenstern’s method of defining bivariate class of distributions with given marginals. The computer simulations and numerical computations were used to investigate the properties of these distributions.

The aim of this diploma thesis was to get familiar with methods to generate surrogates and how to apply them on cardiovascular signals. The first part of this diploma thesis describes the basic theory of baroreflex function and methods to generate surrogate data. Surrogate data were generated from data, acquired from the database, by using three different methods. In the next part of this diploma thesis, coherence significance between blood pressure and heart intervals was calculated by using surrogates. In the end two hypotheses were defined and tested by which it was detected whether the orthostatic change of the measurement position has effect on the causal coherence change and baroreflex function.

No description available.

There exists a debate regarding where to build new housing in increasingly denser cities today. Often it is the green spaces that must be sacrificed which lead to conflicts among decision makers and citizens. Although, some sources claim (Byrne et al., 2010; Van Herzele & Wiedemann, 2003) that it is not only the fact that there is a green area close to you that matters; but rather which values that piece of green land offers you as a citizen. Values of parks can be described as the features or attributes the park area possess that inspire people to go to and stay there. In Stockholm, Sweden these values are connected to sociotopes, a delimited area containing a set of user values with social meaning (Ståhle, 2006). User values thus describes an activity or an experience that is present at a location.  There exists a lack of and a desire for more detailed mapping of user values of green areas as well as a potential need for finding an efficient method for aiding in citizen dialogue when green areas are planned for urban development. The purpose of this thesis is thus to try to incorporate geographical information science (GIS) in urban planning by investigating if it is possible to measure the physical accessibility of user values of a green area before and after its urban development in lines with the recommendations on accessibility from the municipality. Then, try to create a visual tool to be used in the designing phase of urban planning and in citizen dialogue when developing a new urban area. To do this, a case study was done of Årstafältet, a green area in Stockholm that is planned for urban development and improvement of existing and creation of new user values. By using GIS, the user values were defined spatially, and geographical data based on the study area currently as well as after the development where found or created based on descriptions of the new area in planning documents. Accessibility was defined as the physical distance a resident must walk from their home to the closest access point of a user value. Based on previous research, 1000m was deemed the largest distance a resident can walk to be considered a potential user of a user value. An access analysis was made for all residents within the study area to the closest access point of every user value.  The results of the analysis were visualized in two ways, one regarding urban design and another regarding citizen dialogue in the form of bivariate maps and a GIS web application. Apart from the visual maps, some numerical results regarding distance, distance change and number of accessed user values were calculated.   The maps point out the areas that are mostly affected both in the negative and positive sense.  More research needs to be done to decide the best way of deriving and using the numerical measures. Because of the many assumptions and generalizations made in the study it is difficult to make any overall conclusions about the accessibility of user values at Årstafältet. What is more interesting is the reception by people in the field of GIS and urban planning; which was in general positive. They noted upon the important aspect of concretize the design phase of the urban planning process, which often is based on feeling, and create a solid ground to base more informed decisions upon. The visualization methods presented were well received as tools for enabling more people access into the planning process as well as an easy way of exploring geographical data. Also, the possibility to extend this type of access analysis beyond sociotopic user values was deemed as very useful. Lastly, they expressed that this type of analysis is desired by the workers in the field and highly relevant in today’s urban planning process.

No description available.

Studies of diagnostic accuracy often report paired tests for sensitivity and specificity that can be pooled separately to produce summary estimates in a meta-analysis. This was done recently for a systematic review of radiographers' reporting accuracy of plain radiographs. The problem with pooling sensitivities and specificities separately is that it does not acknowledge any possible (negative) correlation between these two measures. A possible cause of this negative correlation is that different thresholds are used in studies to define abnormal and normal radiographs because of implicit variations in thresholds that occur when radiographers' report plain radiographs. A method that allows for the correlation that can exist between pairs of sensitivity and specificity within a study using a random effects approach is the bivariate model. When estimates of accuracy as a fixed-effects model were pooled separately, radiographers' reported plain radiographs in clinical practice at 93% (95% confidence interval (CI) 92-93%) sensitivity and 98% (95% CI 98-98%) specificity. The bivariate model produced the same summary estimates of sensitivity and specificity but with wider confidence intervals (93% (95% CI 91-95%) and 98% (95% CI 96-98%), respectively) that take into account the heterogeneity beyond chance between studies. This method also allowed us to calculate a 95% confidence ellipse around the mean values of sensitivity and specificity and a 95% prediction ellipse for individual values of sensitivity and specificity. The bivariate model is an improvement on pooling sensitivity and specificity separately when there is a threshold effect, and it is the preferred method of choice.

Farmers generally produce multiple crops while selectively adopting modern technologies to meet various needs. The main aim of this study is, therefore, to identify the range of socio-economic factors influencing the adoption of modern agricultural technology in multiple food crops and the corresponding impacts on productivity and food availability at the farm-level in South-eastern Nigeria. In this study, three major food crops (i.e., rice, yam and cassava) and two elements of modern technologies (i.e., HYV seeds and inorganic fertilizers) are considered. The hypotheses of the study are that inverse farm size – technology adoption, size – productivity, size- profitability and size – food availability relationships exist in Nigerian agriculture. The research is based on an in-depth farm-survey of 400 farmers from two states (251 from Ebonyi and 149 from Anambra states) of South-eastern Nigeria. Data has also been derived from surveys and interviews of ADP Program Managers and NGOs. A range of qualitative and quantitative methods including inferential statistics, bivariate probit model and regression analysis were used in order to achieve the specific objectives and test hypotheses. The results show that sample respondents are dominated by small scale farmers (81% of total) owning land less than 1 ha. The average farm size is small estimated at 1.27 ha. Farmers grow multiple crops instead of a single crop, i.e., 68% of the surveyed farmers grew at least two food crops. The level of modern technology adoption is low and mixed and farmers selectively adopt components of technologies as expected and use far less than recommended dose of fertilizers in crops. Only 29% of farmers adopted both HYV seeds and fertilizers as a package. The study clearly demonstrates that inverse farm size – technology adoption, farm size – productivity, and farm size – food availability relationships exist in agriculture in this region of Nigeria; but not inverse farm size – profitability. The bivariate probit model diagnostic reveals that the decision to adopt modern technologies are significantly correlated, implying that univariate analysis of such decisions are biased, thereby, justifying use of the bivariate approach. Overall, the most dominant determinants are the positive influence of farming experience and the negative influence of remoteness of extension services on modern technology adoption. The per capita per day level of mean food produced is 12322.74 calories from one ha of land and food available for consumption is 4693.34 calories which is higher than the daily requirement of 2000 calories. Yam is produced mainly for sale while cassava is produced for consumption. Regression analysis shows that farm size and share of cassava in the total crop portfolio significantly increases food availability. A host of constraints are affecting Nigerian agriculture, which includes lack of extension agents, credit facilities, farm inputs, irrigation, and value addition and corruption, lack of support for ADP staff and ineffective government policies. Policy implications include investment in extension credit services and other infrastructure (e.g., irrigation, ADP staff), training of small farmers in business skills, promotion of modern technology, as a package as well as special projects targeted for cassava (e.g., Cassava Plus project) in order to boost modern technology adoption in food crops, as well as improving productivity, profitability and food availability at the farm-level in Nigeria.

本文選取台灣電子產業發行之11支海外存託憑證(Global Depositary Receipts，GDR)為樣本，其中10支於美國發行、1支於歐盟發行。研究目的分別為國內標的股報酬、存託憑證報酬是否受匯率報酬影響，以及國內、外投資人對匯率風險之看法是否相同。本文選取財務上最常用之估計非線性模型條件共變數之雙變量GARCH(1,1)模型(Bivariate GARCH Model)，經過AIC(Akaike Information Criteria)比較、及相關係數是否隨時間而改變之檢定後，得知所有樣本皆適用DCC(1,1)模型(Dynamic Conditional Correlation Model)，於估計存託憑證報酬與匯率報酬之條件共變數後，再運用多元迴歸模型，探討實證結果。實證結果顯示國內標的股均存在顯著之匯率風險，存託憑證則多數存在顯著之匯率風險。而國內、外投資人對匯率風險之看法異同方面，宏□、鴻海、茂矽、仁寶、錸德、台積電所發行之海外存託憑證，國內、外投資人對存託憑證、國內標的股匯率風險之看法無顯著不同，可歸因於其較其他存託憑證及標的股國際化。而華邦、智邦、旺宏之海外存託憑證，國內、外投資人對存託憑證匯率風險之看法顯著不同，本文又將匯率風險之來源，歸納為兩部分：一、由標的股產生，可歸因於標的股國際化程度；二、由換匯(foreign exchange)產生，可歸因於匯率變動程度；而華邦、智邦、旺宏實證顯示匯率風險皆由標的股產生，因其於美國或歐盟上市，美元或歐元又為強勢貨幣，故不存在換匯風險。