Made available in DSpace on 2015-05-08T14:45:02Z (GMT). No. of bitstreams: 1 arquivototal.pdf: 1380257 bytes, checksum: 1a02e73b7e0ca49d2f010e7b6925950a (MD5) Previous issue date: 2010-04-23 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / This dissertation has as objective to estimate the relationship between monetary policy and the volatility of asset prices using the model BEKK, from January 2003 to October 2009. The specific objectives were: a) model the volatility of the Bovespa Index (Bovespa) and the Selic, referring to the money and stock through GARCH models, b) verify the clustering of volatility, the presence of persistent shocks and perform the analysis half-life in the financial market variables, c) estimate Vector Autoregressive models with the aim of testing the causal relationships in the sense of Granger (Granger Causality) between the transmission mechanism of monetary policy (interest rates) and the index stock; To achieve these objectives we used the model proposed by Bernanke, Gertler (1999, 2000) to describe the effects of volatility in monetary policy rules, and to capture the effects of volatility in monetary policy decisions were used in models family univariate and multivariate GARCH. The test of Granger causality show that there is unidirectional causality Ibovespa Selic regarding the period of greater volatility in the stock market (2003 - 2008), indicating that the returns in the stock market affected the Brazilian monetary policy decisions in this period . The estimation of GARCH models TARCHI and noted the existence of agglomeration of the variance, the effect of leverage on volatility and persistence on the part of stock markets and money. Through the model BEKKER is possible to highlight the volatility of the Selic rate is positively affected by common shocks and their lags inflation volatility, the volatility of the Bovespa index had a direct relationship with the volatility of the Selic rate in the period (2003 - 2008). This fact is consistent with the effects of movements in asset prices on aggregate demand, thus suggesting that policymakers are responding to changes in the market to avoid possible negative impacts on the economy. / Esta dissertação tem como objetivo estimar a relação entre a política monetária e a volatilidade dos preços dos ativos por meio do modelo BEKK, no período de janeiro de 2003 a outubro de 2009. Os objetivos específicos foram: a) modelar a volatilidade do Índice Bovespa (Ibovespa) e da Selic, referentes aos mercados monetário e acionário, por meio de modelos GARCH; b) verificar a aglomeração de volatilidade, presença da persistência dos choques e realizar a análise da meia-vida nas variáveis de mercado financeiro; c) estimar modelos Vetor Autoregressivo com o intuito de testar as relações de causalidade, no sentido de Granger (Granger Causality), entre o mecanismo de transmissão de política monetária (taxa de juros) e o índice acionário; Para atingir tais objetivos foi utilizado o modelo teórico proposto por Bernanke, Gertler (1999, 2000), para descrever os efeitos da volatilidade nas regras de política monetária, e para capturar os efeitos dessa volatilidade nas decisões de política monetária foram utilizados os modelos da família GARCH univariados e multivariados. O resultado do teste de causalidade de Granger mostrou que há causalidade unidirecional do Ibovespa em relação à Selic no período de maior volatilidade no mercado acionário (2003 - 2008), indicando que os retornos no mercado de ações brasileiros afetaram as decisões de política monetária nesse período. A estimação dos modelos TARCH e GARCH apontou a existência de aglomeração da variância, o efeito leverage e a persistência na volatilidade por parte dos mercados de ações e monetário. Por meio do modelo BEKK é possível destacar que a volatilidade da Selic é afetada positivamente por choques comuns as suas defasagens e a volatilidade da inflação; a volatilidade do Ibovespa apresentou uma relação direta com a volatilidade da taxa Selic no período (2003 - 2008). Esse fato é condizente com os efeitos dos movimentos nos preços dos ativos sobre a demanda agregada, sugerindo, portanto, que os policymakers estão reagindo às variações no mercado para evitarem possíveis impactos negativos sobre a economia.

Covid19 hit the world’s financial markets by surprise in March 2020 and ensuing volatility marked an end to the prior low-volatility environment. This Black Swan engendered numerous publications establishing how the equity market responded to the exogenous shock. However, there is no applicable comparison to Nasdaq100 regarding how models perform during extreme conditions such as ante, amid and post Covid19. Furthermore, goodness of fit together with forecasting accuracy are further examined in the light of new intra-day data from Oxford Man Institute covering this time-period. This thesis presents a comparison of volatility models incorporating economic intuition, sentiment, historical values of volatility and stochastics. By exploiting intra-day at 5 min interval the trade-off between noise and loss of valuable information effectively kept at a minimum yielding considerable robustness to the thesis’ result. Linear ARCH-models, Implied Volatility and HARRV applied with the addition of several different combinations of hold-out periods enable multiple vantagepoints for evaluation. This thesis finds HARRV’s series of one-step ahead prediction of future conditional volatility to be superior throughout all hold-out periods. I am able to present empirical evidence supporting the idea that HARRV’s additive cascades of volatility is superior to sentiment-driven implied volatility and ARCH-models pertaining to Nasdaq100.

Made available in DSpace on 2010-04-20T20:14:59Z (GMT). No. of bitstreams: 0 Previous issue date: 1998-02-13T00:00:00Z / Apresenta o método value at risk (VaR) para se mensurar o risco de mercado, sob diferentes abordagens. Analisa a série histórica do índice Bovespa no período de 1995 a 1996 por meio de testes econométricos de normalidade, autocorrelação dos retornos e raiz unitária. Comparo valor obtido a partir dos diferentes modelos de estimação de volatilidade propostos e verifica qual dos modelos foi o mais adequado para o caso estudado. / The purpose of this dissertation is to compare the performance of three methods of volatility estimating used for value at risk models: an exponentially weighted moving average (RiskMetrics TM), GARCH (Generalized Autoregressive Conditional Heteroscedasticity) and TARCH (Threshold model). Concerning the latter, we decided to test it, given that GARCH models cannot properly capture the leverage etTect (negative shocks have a larger impact on volatility than positive shocks). The sample covers the daily São Paulo Stock Exchange index from 2 January 1995 to 30 December 1996. The test results indicated that the alternative models did not outperform RiskMetrics™ under the particular market conditions observed in the time period studied. Despite the fact that TARCH model can cope with negative or positive skewness, this model did not provide better results than RiskMetrics™. It seems to be reasonable not to attempt to make any general statement that one method is undoubtedly superior to another, given that test results may depend on the data period employed.

<p>Syftet med denna uppsats är att med tre GARCH-modeller skatta volatiliteten för fjorton aktier med t- och normalfördelade slumptermer. Dessa volatiliteter implementeras sedan i Black-Scholes modell samt i Monte-Carlo simuleringar och utfallen av dessa två värderingsmetoder jämförs.</p><p>Författarna har kommit fram till att GARCH-modeller behövs för att skatta volatiliteten för de aktier som ingår i arbetet då modellerna tar hänsyn till den föreliggande heteroskedasticiteten.</p><p>De skillnader som uppstår mellan Monte-Carlo simuleringar och Black-Scholes modell beror främst på skillnader mellan normal- och t-fördelningen samt att volatiliteten ger större effekt i Monte-Carlo simuleringarna. Författarna kan inte uttala sig om huruvida Monte-Carlo skattningarna ger bättre resultat än den vedertagna Black-Scholes modell, däremot är Monte-Carlo mer teoretiskt korrekt.</p>

Syftet med denna uppsats är att med tre GARCH-modeller skatta volatiliteten för fjorton aktier med t- och normalfördelade slumptermer. Dessa volatiliteter implementeras sedan i Black-Scholes modell samt i Monte-Carlo simuleringar och utfallen av dessa två värderingsmetoder jämförs. Författarna har kommit fram till att GARCH-modeller behövs för att skatta volatiliteten för de aktier som ingår i arbetet då modellerna tar hänsyn till den föreliggande heteroskedasticiteten. De skillnader som uppstår mellan Monte-Carlo simuleringar och Black-Scholes modell beror främst på skillnader mellan normal- och t-fördelningen samt att volatiliteten ger större effekt i Monte-Carlo simuleringarna. Författarna kan inte uttala sig om huruvida Monte-Carlo skattningarna ger bättre resultat än den vedertagna Black-Scholes modell, däremot är Monte-Carlo mer teoretiskt korrekt.

The thesis evaluates several hundred one-day-ahead VaR forecasting models in the time period between the years 2004 and 2009 on data from six world stock indices - DJI, GSPC, IXIC, FTSE, GDAXI and N225. The models model mean using the AR and MA processes with up to two lags and variance with one of GARCH, EGARCH or TARCH processes with up to two lags. The models are estimated on the data from the in-sample period and their forecasting ac- curacy is evaluated on the out-of-sample data, which are more volatile. The main aim of the thesis is to test whether a model estimated on data with lower volatility can be used in periods with higher volatility. The evaluation is based on the conditional coverage test and is performed on each stock index sepa- rately. Unlike other works in this eld of study, the thesis does not assume the log-returns to be normally distributed and does not explicitly select a partic- ular conditional volatility process. Moreover, the thesis takes advantage of a less known conditional coverage framework for the measurement of forecasting accuracy.