Submitted by Jaqueline Silva (jtas29@gmail.com) on 2016-08-31T18:12:55Z No. of bitstreams: 2 Dissertacao - Millades de Carvalho Castro - 2016.pdf: 2898400 bytes, checksum: bbe10850391e6dda19a8504302660c5b (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) / Approved for entry into archive by Jaqueline Silva (jtas29@gmail.com) on 2016-08-31T18:13:07Z (GMT) No. of bitstreams: 2 Dissertacao - Millades de Carvalho Castro - 2016.pdf: 2898400 bytes, checksum: bbe10850391e6dda19a8504302660c5b (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) / Made available in DSpace on 2016-08-31T18:13:07Z (GMT). No. of bitstreams: 2 Dissertacao - Millades de Carvalho Castro - 2016.pdf: 2898400 bytes, checksum: bbe10850391e6dda19a8504302660c5b (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Previous issue date: 2016-06-03 / Fundação de Amparo à Pesquisa do Estado de Goiás - FAPEG / Volatility in the prices of commodities and the financial return of agricultural activities affect the choice of what to produce. The present work investigates volatilities in prices of cattle, soybeans, and corn in Rio Verde (GO, Brazil), the choice of this region should be the importance of the city in the state and national agricultural production. For this study, we analyze weekly prices of corn, soybeans and cattle in Rio Verde spot market from 2004 to 2014, using Time Series Analysis and Value at Risk. The examination of the series pointed to the presence of a conditional variance. Therefore the ARCH / GARCH models were applied. The model selected to soybean was the IGARCH (2.1) and to corn and cattle the EGARCH (1.1). Due to disproportion between the traded prices and volumes it was not possible to perform the VAR series comparison. Therefore we used the ratio between the VAR and revenue of each product to compare between markets. Results showed a higher ratio for the cattle series indicating that volatility affects cattle producers’ income more than that of soybean or corn producers in Rio Verde (GO), which resulted in the reduction of this activity in the region. / A volatilidade nos preços das commodities e o retorno financeiro das atividades agropecuárias afetam a escolha do que produzir. O presente trabalho visa investigar as volatilidades nos preços do boi e das culturas de soja e milho para o município de Rio Verde (GO, Brasil), no período de 2004 a 2014, a escolha dessa região deve-se a importância do município na produção agropecuária estadual e nacional. Para tanto, utilizou-se de dados semanais de preços de milho, soja e boi no mercado físico de Rio Verde no período de 2004 a 2014. A metodologia usada foi a usual de análise de séries temporais e cálculo do Value at Risk (VaR). O exame das séries apontou a presença de variância condicional, sendo então aplicados os modelos ARCH/GARCH.O modelo selecionado para soja foi o IGARCH (2,1) e para milho e boi o EGARCH (1,1). Posteriormente, o cômputo do VaR para cada uma das séries não é suficiente para comparação, devido a desproporção entre os preços e os volumes negociados. Logo, para que fosse possível a comparação entre os mercados, utilizou-se da razão entre VaR e a receita de cada produto. Os resultados apontaram que em média, a razão foi maior para a série bovina. Portanto, a volatilidade compromete a receita dos produtores bovinos mais do que os agricultores de milho e soja no município de Rio Verde (GO), o que implicou na redução dessa atividade na região.

Neste trabalho analisaremos a utilização dos modelos de mudança de regime markoviano para a variância condicional. Estes modelos podem estimar de maneira fácil e inteligente a variância condicional não observada em função da variância anterior e do regime. Isso porque, é razoável ter coeficientes variando no tempo dependendo do regime correspondentes à persistência da variância (variância anterior) e às inovações. A noção de que uma série econômica possa ter alguma variação na sua estrutura é antiga para os economistas. Marcucci (2005) comparou diferentes modelos com e sem mudança de regime em termos de sua capacidade para descrever e predizer a volatilidade do mercado de valores dos EUA. O trabalho de Hamilton (1989) foi uns dos mais importantes para o desenvolvimento de modelos com mudança de regime. Inicialmente mostrou que a série do PIB dos EUA pode ser modelada como um processo que tem duas formas diferentes, uma na qual a economia encontra-se em crescimento e a outra durante a recessão. O câmbio de uma fase para outra da economia pode seguir uma cadeia de Markov de primeira ordem. Utilizamos as séries de índice Bovespa e S&P500 entre janeiro de 2003 e abril de 2012 e ajustamos o modelo GARCH(1,1) com mudança de regime seguindo uma cadeia de Markov de primeira ordem, considerando dois regimes. Foram consideradas as distribuições gaussiana, t de Student e generalizada do erro (GED) para modelar as inovações. A distribuição t de Student com mesmo grau de liberdade para ambos os regimes e graus distintos se mostrou superior à distribuição normal para caracterizar a distribuição dos retornos em relação ao modelo GARCH com mudança de regime. Além disso, verificou-se um ganho no percentual de cobertura dos intervalos de confiança para a distribuição normal, bem como para a distribuição t de Student com mesmo grau de liberdade para ambos os regimes e graus distintos, em relação ao modelo GARCH com mudança de regime quando comparado ao modelo GARCH usual. / In this work we analyze heterocedastic financial data using Markov regime switching models for conditional variance. These models can estimate easily the unobserved conditional variance as function of the previous variance and the regime. It is reasonable to have time-varying coefficients corresponding to the persistence of variance (previous variance) and innovations. The economic series notion may have some variation in their structure is usual for economists. Marcucci (2005) compared different models with and without regime switching in terms of their ability to describe and predict the volatility of the U.S. market. The Hamiltons (1989) work was the most important one in the regime switching models development. Initially showed that the series of U.S. GDP can be modeled as a process that has two different forms one in which the economy is growing and the other during the recession. The change from one phase to another economy can follow a Markov first order chain. We use the Bovespa series index and S&P500 between January 2003 and April 2012 and fitted the GARCH (1,1) models with regime switching following a Markov first order chain, considering two regimes. We considered Gaussian distribution, Student-t and generalized error (GED) to model innovations. The t-Student distribution with the same freedom degree for both regimes and distinct degrees showed higher than normal distribution for characterizing the distribution of returns relative to the GARCH model with regime switching. In addition, there was a gain in the percentage of coverage of the confidence intervals for the normal distribution, as well as the t-Student distribution with the same freedom degree for both regimes and distinct degrees related to GARCH model with regime switching when compared to the usual GARCH model.

自從2008年金融危機爆發後，黑天鵝事件相繼出現，VIX成為投資人衡量股市波動度的重要指標。但是若投資人想使用VIX避險，僅能透過限專業投資人參與的VIX期貨。而在近年ETF產品盛行的背景下，投資標的更加多元的交易所交易債券（ETN）也應運而生，使一般投資人得以進入以往難以觸及或交易成本高昂的市場。本研究採用兩檔交易量較大之VIX ETN，分別追蹤VIX短期與中期期貨指數之VXX與VXZ，希望透過建構GARCH模型用以預測其隔日價格，並以此預測的價格近一步建構避險策略，目標係在預期空頭即將發生時，提供投資人除了VIX期貨和波動相對平穩的債券以外的避險替代工具。 建構GARCH模型的部分，本研究主要參考Kambouroudis和McMillan（2013）的文獻，在變異數方程式中加入輔助變數，可以增加模型的預測能力，故本研究在VIX ETN之GARCH模型的變異數方程式中加入VIX、短期VIX指數及中期VIX指數。實證結果顯示，在VIX ETN的GARCH模型中同時加入VIX相關指數，確實能提高配適程度並增進預測能力，尤其當加入的輔助變數與VIX ETN追蹤標的的到期期限相符時，此改善模型的效果最為顯著。 本研究接者參考Alexander和Korovilas（2012）的VIX ETN避險研究，文獻顯示，在S&P 500 ETF投資組合中加入VXX與VXZ避險可提高夏普比率。本研究在此基礎上，額外考量了不同的持有期間、進場條件、股債混合的投資組合，並分別比較兩種ETN的避險效果。本研究發現只在VIX大於20時才進場建構避險部位的策略，提前買入VIX ETN確實可以做為良好的避險工具。此外，在此策略下，VIX ETN亦則可達到比持有債券更佳的避險效果。而本研究所測試的兩種VIX ETN中，又以VXX 避險效果更佳，因VXX乃是追蹤VIX短期期貨指數，更能反映市場短期的變化，搭配滾動的避險比率，能更加精準的反應空頭時期劇烈的波動。 / Since the 2008 financial crisis, along with the black swan events, the volatility of global stock market has intensified, and VIX index becomes an important indicator for investors to measure the volatility of the stock market. However, if investors would like to use VIX index for hedge, they could only use VIX futures, which is only for professional investors to participate. In recent years, the prevalence and popularity of the various ETPs lead to the booming of VIX ETNs, which has become an alternative for regular investors to invest in VIX index. Therefore, this study hopes to build GARCH model for VIX ETN and predict their prices of the next day, and use the prediction to build hedging strategies. In this paper, this study mainly refers to the paper of Kambouroudis and McMillan (2013) to construct the VXX and VXZ prediction models. Because the two VIX ETNs track the S&P 500 VIX short-term and medium-term futures index respectively, the study add the VIX index, short-term VIX index and medium-term VIX index in the GARCH models. The empirical results show that the addition of VIX and other relevant VIX indices in the VIX ETN GARCH models can improve the forecasting ability. In particular, when the maturity of the VIX index is consistent with the maturity of the VIX ETN’s tracking target, it would improve the prediction power the most. Based on the predicted VIX ETN prices, this study then constructs the hedging strategies, considering the different holding period, the entry condition and the stock and debt mixed portfolio, and also compares the hedging effect of VXX and VXZ respectively. This study found that under the strategy that only enter the VIX ETN market when VIX was greater than 20, VIX ETN can indeed be a good hedge tool and reduce the standard deviation of the portfolio. In addition, under this strategy, if investors use VIX ETN to hedge, investors can achieve a higher return and lower standard deviation than holding a bond to hedge. Finally, among the two VIX ETNs tested in this study, VXX is a better hedge tool against VXX. It is because VXX tracks the VIX short-term futures index which reflects the short-term changes in the market and hence could reflect the short-term volatility better.

The global economy has been severely impacted during the Covid-19 period. The U.S. stock market has also experienced greater volatility. Based on data from January 2020 to June 2021, this paper studies the volatility of daily returns on the stock market in the United States. The Standard and Poor's 500 (SPX) index and eight companies traded on major exchanges such as the New York Stock Exchange and the Nasdaq are used to calculate volatility. Combining the statistical analysis methods GARCH, GARCH-M, and TARCH, the time series of each security is modeled. It is demonstrated that the conditional heteroskedasticity of stock returns depends not only on the observed historical volatility (ARCH term) but also on the conditional heteroskedasticity of prior periods (GARCH term). As expected for financial markets, the COVID-19 outbreak increased the volatility of U.S. stock market returns. After the COVID-19 outbreak, the volatility of the U.S. stock market rose dramatically. It reached an extremely high level for the first quarter of 2020 and continued to move downwards in the following quarters. The significant heteroskedasticity in the return volatility indicates that external variables significantly affect the stock. Furthermore, this study combines the Capital Asset Pricing Model (CAPM) and the research of Engle et al. (1987), which provides a way to quantify the liquidity premium. However, with the results of the GARCH-M model, this study does not find a significant liquidity premium over time. Additionally, The TARCH model reveals a significant asymmetry in stock market returns during this epidemic, suggesting that negative news has a more substantial impact on U.S. financial markets. For investors and financial institutions, this research helps identify potential volatility in the face of similar risk events. It is helpful for investors to comprehensively consider various factors when investing in special periods or consider other investment portfolios to reduce investment risks in specific periods based on research results.

Yes / This paper studies the predictive ability of corridor implied volatility (CIV) measure. It is motivated by the fact that CIV is measured with better precision and reliability than the model-free implied volatility due to the lack of liquid options in the tails of the risk-neutral distribution. By adding CIV measures to the modified GARCH specifications, the out-of-sample predictive ability of CIV is measured by the forecast accuracy of conditional volatility. It finds that the narrowest CIV measure, covering about 10% of the RND, dominate the 1-day ahead conditional volatility forecasts regardless of the choice of GARCH models in high volatile period; as market moves to non volatile periods, the optimal width broadens. For multi-day ahead forecasts narrow and mid-range CIV measures are favoured in the full sample and high volatile period for all forecast horizons, depending on which loss functions are used; whereas in non turbulent markets, certain mid-range CIV measures are favoured, for rare instances, wide CIV measures dominate the performance. Regarding the comparisons between best performed CIV measures and two benchmark measures (market volatility index and at-the-money Black–Scholes implied volatility), it shows that under the EGARCH framework, none of the benchmark measures are found to outperform best performed CIV measures, whereas under the GARCH and NAGARCH models, best performed CIV measures are outperformed by benchmark measures for certain instances.

Nas últimas décadas a volatilidade transformou-se num conceito muito importante na área financeira, sendo utilizada para mensurar o risco de instrumentos financeiros. Neste trabalho, o foco de estudo é a modelagem da volatilidade, que faz referência à variabilidade dos retornos, sendo esta uma característica presente nas séries temporais financeiras. Como ferramenta fundamental da modelação usaremos o modelo GARCH (Generalized Autoregressive Conditional Heteroskedasticity), que usa a heterocedasticidade condicional como uma medida da volatilidade. Considerar-se-ão duas características principais a ser modeladas com o propósito de obter um melhor ajuste e previsão da volatilidade, estas são: a assimetria e as caudas pesadas presentes na distribuição incondicional da série dos retornos. A estimação dos parâmetros dos modelos propostos será feita utilizando a abordagem Bayesiana com a metodologia MCMC (Markov Chain Monte Carlo) especificamente o algoritmo de Metropolis-Hastings. / In the last decades volatility has become a very important concept in the financial area, being used to measure the risk of financial instruments. In this work, the focus of study is the modeling of volatility, that refers to the variability of returns, which is a characteristic present in the financial time series. As a fundamental modeling tool, we used the GARCH (Generalized Autoregressive Conditional Heteroskedasticity) model, which uses conditional heteroscedasticity as a measure of volatility. Two main characteristics will be considered to be modeled with the purpose of a better adjustment and prediction of the volatility, these are: heavy tails and an asymmetry present in the unconditional distribution of the return series. The estimation of the parameters of the proposed models is done by means of the Bayesian approach with an MCMC (Markov Chain Monte Carlo) methodology , specifically the Metropolis-Hastings algorithm.

O presente trabalho analisou as volatilidades dos mercados de renda fixa e variável de onze países, sendo eles: Brasil, Rússia, Índia, China, África do Sul (neste país apenas renda fixa), Argentina, Chile, México, Estados Unidos, Alemanha e Japão no período de janeiro de 2000 a dezembro de 2011. Os indicadores utilizados para representar cada mercado foram os índices dos mercados de ações e as taxas de juros interbancárias. Para tanto, o estudo se utilizou de modelos de heterocedasticidade condicional auto-regressiva: ARCH, GARCH, EGARCH, TGARCH e PGARCH, verificando quais destes processos eram mais eficientes para modelagem da volatilidade dos mercados dos países da amostra. Esta pesquisa também verificou qual dos modelos (ARIMA ou modelos GARCH e suas extensões) conseguiria prever melhor as séries de tempo analisadas. Além disso, por meio dos índices de correlação, covariância e causalidade Granger, foram comparados os retornos e a volatilidade do mercado de ações entre os países BRIC, entre os países latinos americanos e entre os países desenvolvidos e o Brasil. Os resultados sugerem que a volatilidade, tanto do mercado de renda fixa quanto do mercado de renda variável, é mais bem modelada por processos GARCH assimétricos (EGARCH e TGARCH), demonstrando efeitos de alavancagem nas séries estudadas. Quanto aos modelos de previsão, os modelos ARIMA, também para os dois mercados, mostrou-se mais eficiente que os modelos GARCH e suas extensões. Além disso, as volatilidades dos mercados de ações entre os países analisados parecem ser mais correlacionadas e possuir maior causalidade Granger do que os retornos destes países. Entre os dois mercados, renda fixa e variável dentro de cada país, as correlações dos retornos e da volatilidade são muito baixas, em algumas vezes negativa, e há pouca relação de causalidade Granger. / This study analyzed the volatility of fixed income and stocks markets for eleven countries, namely: Brazil, Russia, India, China, South Africa (just fixed income), Argentina, Chile, Mexico, United States, Germany and Japan from January 2000 to December 2011, using interbank interest rate as a fixed income market indicator and stock index to each country, as a stock market indicator. Therefore, the study used models of autoregressive conditional heteroscedasticity: ARCH, GARCH, EGARCH, TGARCH e PGARCH to verify which of these processes were more effective for in volatility modeling in each country. This research also found that the models (ARIMA or GARCH models and their extensions) could be used as the best forecast models. Moreover, by means of correlation coefficients, covariance and Granger causality, were used to compare the returns and volatility of the stock market among the BRIC countries, among the Latin American countries and between developed countries and Brazil. The results suggest that the volatility of both the fixed income market as the stock market is best modeled by processes asymmetric GARCH (EGARCH and TGARCH) demonstrating leverage effects in the time series. Regarding prediction ARIMA models was more efficient for both markets than GARCH models and extensions. In addition, the volatility of stock markets across countries analyzed seem to be more correlated and have higher Granger causality than returns these countries. Between the two markets, for each country, the correlations of returns and volatility are very low, if not positive, and there is low Granger causality.

A modelagem da volatilidade desempenha um papel fundamental em Econometria. Nesta dissertação são estudados a generalização dos modelos autorregressivos condicionalmente heterocedásticos conhecidos como GARCH e sua principal generalização multivariada, os modelos DCC-GARCH (Dynamic Condicional Correlation GARCH). Para os erros desses modelos são consideradas distribuições de probabilidade possivelmente assimétricas e leptocúrticas, sendo essas parametrizadas em função da assimetria e do peso nas caudas, necessitando assim de estimar esses parâmetros adicionais aos modelos. A estimação dos parâmetros dos modelos é feita sob a abordagem Bayesiana e devido às complexidades destes modelos, métodos computacionais baseados em simulações de Monte Carlo via Cadeias de Markov (MCMC) são utilizados. Para obter maior eficiência computacional os algoritmos de simulação da distribuição a posteriori dos parâmetros são implementados em linguagem de baixo nível. Por fim, a proposta de modelagem e estimação é exemplificada com dois conjuntos de dados reais / The modeling of volatility plays a fundamental role in Econometrics. In this dissertation are studied the generalization of known autoregressive conditionally heteroscedastic (GARCH) models and its main principal multivariate generalization, the DCCGARCH (Dynamic Conditional Correlation GARCH) models. For the errors of these models are considered distribution of probability possibility asymmetric and leptokurtic, these being parameterized as a function of asymmetry and the weight on the tails, thus requiring estimate the models additional parameters. The estimation of parameters is made under the Bayesian approach and due to the complexities of these models, methods computer-based simulations Monte Carlo Markov Chain (MCMC) are used. For more computational efficiency of simulation algorithms of posterior distribution of the parameters are implemented in low-level language. Finally, the proposed modeling and estimation is illustrated with two real data sets

O conhecimento do risco de ativos financeiros é de fundamental importância para gestão ativa de carteiras, determinação de preços de opções e análise de sensibilidade de retornos. O risco é medido através da variância estatística e há na literatura diversos modelos econométricos que servem a esta finalidade. Esta pesquisa contempla o estudo de modelos determinísticos de volatilidade, mais especificamente os modelos GARCH simétricos e assimétricos. O período de análise foi dividido em dois: de janeiro de 2000 à fevereiro de 2008 e à outubro de 2008. Tal procedimento foi adotado procurando identificar a influência da crise econômica originada nos EUA nos modelos de volatilidade. O setor escolhido para o estudo foi o mercado de petróleo e foram escolhidas as nove maiores empresas do setor de acordo com a capacidade produtiva e reservas de petróleo. Além destas, foram modeladas também as commodities negociadas na Bolsa de Valores de Nova York: o barril de petróleo do tipo Brent e WTI. A escolha deste setor deve-se a sua grande importância econômica e estratégica para todas as nações. Os resultados encontrados mostraram que não houve um padrão de modelo de volatilidade para todos os ativos estudados e para a grande maioria dos ativos, há presença de assimetria nos retornos, sendo o modelo GJR (1,1) o que mais prevaleceu, segundo a modelagem pelo método da máxima verossimilhança. Houve aderência, em 81% dos casos, dos ativos a um determinado modelo de volatilidade, alterando apenas, como eram esperados, os coeficientes de reatividade e persistência. Com relação a estes, percebe-se que a crise aumentou os coeficientes de reatividade para alguns ativos. Ao se compararem as volatilidades estimadas de curto prazo, percebe-se que o agravamento da crise introduziu uma elevação média de 265,4% em relação ao período anterior, indicando um aumento substancial de risco. Para a volatilidade de longo prazo, o aumento médio foi de 7,9%, sugerindo que os choques reativos introduzidos com a crise, tendem a ser dissipados ao longo do tempo. / The knowledge of the risk of financial assets is of basic importance for active management of portfolios, determination of prices of options and analysis of sensitivity of returns. The risk is measured through the variance statistics and has in literature several econometrical models that serve to this purpose. This research contemplates the study of deterministic models of volatility, more specifically symmetrical and asymmetrical models GARCH. The period of analysis was divided in two: January of 2000 to the February of 2008 and the October of 2008. Such a proceeding was adopted trying to identify the influence of the economic crisis given rise in U.S.A. in the volatility models. The sector chosen for the study was the oil market and had been chosen the nine bigger companies of the sector in accordance with the productive capacity and reserves of oil. Beyond these, there were modeled also the commodities negotiated in the Stock Exchange of New York: the barrel of oil of the types Brent and WTI. The choice of this sector is due to his great economical and strategic importance for all the nations. The results showed that there was no a standard of model of volatility for all the studied assets and for the majority of them, there is presence of asymmetry in the returns, being the model GJR (1,1) that more prevailed, according to the method of likelihood. There was adherence, in 81 % of the cases, of the assets to a determined model of volatility, altering only the coefficients of reactivity and persistence. Regarding these, it is realized that the crisis increased the coefficients of reactivity for some assets. In relation to the volatilities of short term, it is realized that the aggravation of the crisis introduced an elevation of 265,4% regarding the previous period, indicating a substantial increase of risk. In relation to the volatility of long term, the increase was 7,9 %, suggesting that the reactive shocks introduced with the crisis have a tendency to be dispersed along the time.

In this study, both uni-regime GARCH and Markov Regime Switching GARCH (SW-GARCH) models are examined to analyze Turkish Stock Market volatility. We investigate various models to find out whether SW-GARCH models are an improvement on the uni-regime GARCH models in terms of modelling and forecasting Turkish Stock Market volatility. As well as using seven statistical loss functions, we apply Superior Predictive Ability (SPA) test of Hansen (2005) and Reality Check test (RC) of White (2000) to compare forecast performance of various models.