The master's thesis deals with modeling Value at Risk model adjusted by liquid- ity. For this purpose we use quantile regression analysis and liquidity proxies. We find out that Garman-Klass volatility estimator can be very useful in pe- riod 2000-2008 for the small and mid-size semiconductor companies but not in period 2008-2015. The NASDAQ composite Garman-Klass volatility is useful for all semiconductor companies for period 2008-2015. We might conclude that from the outbreak of the crisis returns of all semiconductor companies might depend on movement of NASDAQ composite index. We use Amihud and Roll measures as the liquidity proxies but the results are not persuasive regardless or size of companies and period we analyzed. JEL Classification G11, G14, G17, G18, G32 Keywords liquidity, value at risk, quantile regression Author's e-mail michalnd@gmail.com Supervisor's e-mail barunik@utia.cas.cz Abstrakt Diplomová práce se zabývá modelováním hodnoty v risku upravenou o likvid- itu. Pro tuto analýzu jsme použili kvantilovou regresi a proměnné indikující likviditu. Došli jsme k závěru, že Garman-Klass volatility estimator je velmi užitečný pro malé a středně velké firmy operující na trhu s polovodiči a to v ob- dobí 2000-2007, nikoliv však období 2008-2015. NASDAQ composite...

This work analyzes the contagion effects between energy and CEE financial markets during the two crisis periods (global financial crisis 2008-2009 and energy market crisis 2014), using a sample of daily data from 2004 till 2015. We detect contagion by observing the degree and structure of two dummy variables for specified crisis periods included into the quantile regression models on the basis of a dependence measure called "coexceedances". Our results show that there are significant contagion effects present between the gasoil and CEE stock markets during the 2008-2009 period and mixed evidence of contagion between crude oil market and CEE stock markets. CEE stock markets do not appear to exhibit significant contagion effects with energy markets during the recent energy market crisis. These results substantially differ from those found in the developed European markets. In particular, our results indicate that energy markets and stock markets in developed Europe seem to display significant contagion effects during the 2014-2015 period. Keywords: Central and Eastern Europe, contagion, energy market, quantile regression

A relação professor-aluno é fator essencial no processo de desenvolvimento físico, social e emocional dos alunos, principalmente em se tratando de alunos da primeira infância, sendo este o momento de maior aprendizado em nossas vidas. Desta forma, estruturar uma boa relação com a criança permite ao professor consolidar um ambiente propício e estimulante ao ensino, além de facilitar ajustes comportamentais. Assim, este trabalho busca captar efeitos determinantes para uma boa relação professor-aluno, mais especificamente via nível de amabilidade do professor. Esta análise foi possível utilizando dados da cidade de Petrolina, coletadas pelo Instituto Alfa e Beto, contendo informações a respeito da escala de relação professor-aluno (ERPA) e o nível de amabilidade do professor via instrumento SENNA. O município de Petrolina utilizou-se do processo de convênio para expandir o número de vagas em educação infantil através do projeto denominado \"Nova Semente\". Entretanto, constatamos características divergentes entre a rede pública e conveniada sobre a composição da equipe de docentes, de forma que estas indiquem um cenário de baixa qualidade no ensino oferecido pela rede conveniada. Por fim, encontramos vestígios de que maiores níveis de amabilidade do professor de creche compensa em partes uma baixa qualificação. / The teacher-child relationship is an essential factor in the process of physical, social and emotional achievement of the students, especially in early childhood, the moment of highest development in the life. This way, structuring a good relationship with the child, allows the teacher not only consolidating a favorable and stimulant learning environment, but also provide behavioral adjustment. Therefore, this study aims at show determinants of a good teacher-child relationship, more specifically by teacher agreeableness. The analysis became possible by the use of a database from Petrolina (PE, Brazil) collected by Alfa e Beto Institute, which contains information related to a scale of teacher-child relationship (ERPA) and the score of teacher agreeableness measured by SENNA instrument. The city of Petrolina used the agreement process to increase the number of vacancies in early childhood education day care centers through a project named \"Nova Semente\" (New Seed). Distinct characteristics were registered between the public and chartered projects regarding the composition of teaching staff, indicating a low quality income in teaching process offered by chartered sector. It is fair to infer that teacher agreeableness in day care center compensates for low training level of teaching staff.

In this thesis we analyse the impact of uncertainty shocks in the Scandinavian banking sector. We apply the spillover approach developed by Diebold and Yilmaz (2009; 2012; 2014), followed by network analysis. Furthermore, the dynamics of uncertainty shocks are examined by applying a quantile regression approach. We study the effects of financial uncertainty, economic policy uncertainty, geopolitical risk and housing market uncertainty on the seven banks Swedbank, Nordea, SEB, Svenska Handelsbanken, DNB, Danske Bank and Jyske Bank. We study these uncertainties on global, regional and local level between 2005 and 2018. We find that the Swedish banks are greater emitters of contagion, compared to the Norwegian and Danish banks, where SEB and Nordea are the banks emitting and receiving the most spillovers. Moreover, the connectedness within the banking sector tend to increase in times of heightened uncertainty, such as during the Global Financial Crisis and the European Sovereign Debt Crisis. Global financial uncertainty is shown to affect the Scandinavian banks the most, followed by regional and local financial uncertainty. The same pattern can be seen for economic policy uncertainty, although at lower levels of spillovers. Reversely, housing market uncertainty is seen to increase going from global, regional to local, where the impact of local housing market uncertainty has a considerable amount of spillovers to the Scandinavian banks. Geopolitical risk is shown to have limited spillovers to the Scandinavian banks. The result of the quantile regressions suggests that financial uncertainty is affecting the banks’ returns negatively during bearish market conditions, whilst the relationship is positive during bullish market conditions. Moreover, we find that financial uncertainty is a quicker transmitter of spillovers than housing market uncertainty. Finally, we conclude that uncertainty shocks affecting the Scandinavian banks negatively tend to take effect instantaneously, while the effects of positive shocks are delayed.

Este trabalho trata de modelos de regressão quantílica. Foi feita uma introdução a essa classe de modelos para motivar a discussão. Em seguida, conceitos inferenciais, como estimação, intervalos de confiança, testes de hipóteses para os parâmetros são discutidos, acompanhados de alguns estudos de simulação. Para analisar a qualidade do ajuste, são apresentados o coeficiente de determinação e um teste de falta de ajuste para modelos de regressão quantílica. Também é proposta a utilização de gráficos para análise da qualidade do ajuste considerando a distribuição Laplace Assimétrica. Uma aplicação utilizando um banco de dados com informação sobre renda no Brasil foi utilizado para exemplificar os tópicos discutidos durante o texto. / This work is about quantile regression models. An introduction was made to this class of models to motivate the discussion. Then, inferential concepts, like estimation, confidence intervals, tests of hypothesis for the parameters are discussed, followed by some simulation studies. To analyse goodness of fit, a coefficient of determination and a lack-of-fit test for quantile regression models are presented. Its also proposed the use of graphs for the goodness of fit analysis considering the Asymmetric Laplace Distribution. An application using a data base with information about income in Brazil was used to exemplify the topics discussed during the text.

In a regression context, the aim is to analyse a response variable of interest conditional to a set of covariates. In many applications the response variable is discrete. Examples include the event of surviving a heart attack, the number of hospitalisation days, the number of times that individuals benefit of a health service, and so on. This thesis advances the methodology and the application of regression models with discrete response. First, we present a difference-in-differences approach to model a binary response in a health policy evaluation framework. In particular, generalized linear mixed methods are employed to model multiple dependent outcomes in order to quantify the effect of an adopted pay-for-performance program while accounting for the heterogeneity of the data at the multiple nested levels. The results show how the policy had a positive effect on the hospitals' quality in terms of those outcomes that can be more influenced by a managerial activity. Next, we focus on regression models for count response variables. In a parametric framework, Poisson regression is the simplest model for count data though it is often found not adequate in real applications, particularly in the presence of excessive zeros and in the case of dispersion, i.e. when the conditional mean is different to the conditional variance. Negative Binomial regression is the standard model for over-dispersed data, but it fails in the presence of under-dispersion. Poisson-Inverse Gaussian regression can be used in the case of over-dispersed data, Generalised-Poisson regression can be employed in the case of under-dispersed data, and Conway-Maxwell Poisson regression can be employed in both cases of over- or under-dispersed data, though the interpretability of these models is ot straightforward and they are often found computationally demanding. While Jittering is the default non-parametric approach for count data, inference has to be made for each individual quantile, separate quantiles may cross and the underlying uniform random sampling can generate instability in the estimation. These features motivate the development of a novel parametric regression model for counts via a Discrete Weibull distribution. This distribution is able to adapt to different types of dispersion relative to Poisson, and it also has the advantage of having a closed form expression for the quantiles. As well as the standard regression model, generalized linear mixed models and generalized additive models are presented via this distribution. Simulated and real data applications with different type of dispersion show a good performance of Discrete Weibull-based regression models compared with existing regression approaches for count data.

This thesis is focused on wages models on the czech labor market in 1996 and 2002. Wages models are built on non-trivial mathematical background and parameters of given models are estimated by methods based on sum of squared residuals and also not often used quantile regression. The quantile regression theory is described in the thesis together with test statistics. Properties of estimations, demonstration examples and proposal of practical application are also indroduced. The theory was applied to two large-size data-files, recieved results show the difference between years 1996 and 2002; a comparison with European Union countries is also given.

Este trabalho trata de modelos de regressão quantílica. Foi feita uma introdução a essa classe de modelos para motivar a discussão. Em seguida, conceitos inferenciais, como estimação, intervalos de confiança, testes de hipóteses para os parâmetros são discutidos, acompanhados de alguns estudos de simulação. Para analisar a qualidade do ajuste, são apresentados o coeficiente de determinação e um teste de falta de ajuste para modelos de regressão quantílica. Também é proposta a utilização de gráficos para análise da qualidade do ajuste considerando a distribuição Laplace Assimétrica. Uma aplicação utilizando um banco de dados com informação sobre renda no Brasil foi utilizado para exemplificar os tópicos discutidos durante o texto. / This work is about quantile regression models. An introduction was made to this class of models to motivate the discussion. Then, inferential concepts, like estimation, confidence intervals, tests of hypothesis for the parameters are discussed, followed by some simulation studies. To analyse goodness of fit, a coefficient of determination and a lack-of-fit test for quantile regression models are presented. Its also proposed the use of graphs for the goodness of fit analysis considering the Asymmetric Laplace Distribution. An application using a data base with information about income in Brazil was used to exemplify the topics discussed during the text.

The objective of this study is to address some important questions associated with stomach cancer patients using the data from the Surveillance Epidemiology and End Results (SEER) program of the United States. To better understand the behavior of stomach cancer, we first perform parametric analysis for each patient group (white male, white female, African American male, African American female, other male and female) to identify the probability distribution function which can best characterize the behavior of the malignant stomach tumor sizes. We evaluate the effects of patients’ age, gender and race on the malignant stomach tumor sizes by developing quantile regression models, which gives us a better understanding of the behavior of the malignant stomach tumors. We also proposed statistical models with respect to patients’ malignant stomach tumor size as a function of age for different races and gender group, respectively. The proposed models were evaluated to attest their prediction quality. Furthermore, we have identified the rate of change of the malignant tumor size as a function of age, for gender and race. We evaluated the routine treatment of stomach cancer using parametric and nonparametric survival analysis. We have found that stomach cancer patients who receive surgery with radiation together have a better survival probability than the patients who receive only radiation. We performed decision tree analysis to assist the physician in recommending to his patients the most effective treatment that is a function of their characteristics.

<p>Quantile regression have its advantage properties comparing to the OLS model regression which are full measurement of the effects of a covariate on response, robustness and Equivariance property. In this paper, I use a survey data in Belgium and apply a linear model to see the advantage properites of quantile regression. And I use a quantile regression model with the raw data to analyze the different cost of family on different numbers of children and apply a Wald test. The result shows that for most of the family types and living standard, from the lower quantile to the upper quantile the family cost on children increases along with the increasing number of children and the cost of each child is the same. And we found a common behavior that the cost of the second child is significantly more than the cost of the first child for a nonworking type of family and all living standard families, at the upper quantile (from 0.75 quantile to 0.9 quantile) of the conditional distribution.</p>