This paper discusses the performance of modeling and forecasting volatility ofdaily stock returns of A-shares in Shanghai Stock Exchange. The volatility is modeledby GARCH family models which are GARCH, EGARCH and GJR-GARCHmodels with three distributions, namely Gaussian distribution, student-t distributionand generalized error distribution (GED). In order to determine the performanceof forecasting volatility, we compare the models by using the Root MeanSquared Error (RMSE). The results show that the EGARCH models work so wellin most of daily stock returns and the symmetric GARCH models are better thanasymmetric GARCH models in this paper.

<p>Condfidence in the future is a signicant factor for business development. However frequently, accurate and specific purposes are spread over the market environment influence.Thus,it is necessary to make an appropriate consideration of instability, which is peculiar to the dynamic development. Volatility, variance and standard deviation are used to</p><p>characterize the deviation of the investigated quantity from mean value.</p><p>Volatility is one of the main instruments to measure the risk of the asset.</p><p>The increasing availability of financial market data has enlarged volatility research potential but has also encouraged research into longer horizon volatility forecasts.</p><p>In this paper we investigate stock index volatility with respect to capitalization with help of GARCH-modelling.</p><p>There are chosen three indexes of OMX Nordic Exchange for our research. The Nordic list segment indexes comprising Nordic Large Cap,</p><p>Mid Cap and Small Cap are based on the three market capitalization groups.</p><p>We implement GARCH-modeling for considering indexes and compare our results in order to conclude which ones of the indexes is more volatile.</p><p>The OMX Nordic list indexis quiet new(2002)and reorganized as late as October 2006. The current value is now about 300 and no options do exist. In current work we are also interested in estimation of the Heston</p><p>model(SVmodel), which is popular in financial world and can be used in option pricing in the future.</p><p>The results of our investigations show that Large Cap Index is more volatile then Middle and Small Cap Indexes.</p>

Condfidence in the future is a signicant factor for business development. However frequently, accurate and specific purposes are spread over the market environment influence.Thus,it is necessary to make an appropriate consideration of instability, which is peculiar to the dynamic development. Volatility, variance and standard deviation are used to characterize the deviation of the investigated quantity from mean value. Volatility is one of the main instruments to measure the risk of the asset. The increasing availability of financial market data has enlarged volatility research potential but has also encouraged research into longer horizon volatility forecasts. In this paper we investigate stock index volatility with respect to capitalization with help of GARCH-modelling. There are chosen three indexes of OMX Nordic Exchange for our research. The Nordic list segment indexes comprising Nordic Large Cap, Mid Cap and Small Cap are based on the three market capitalization groups. We implement GARCH-modeling for considering indexes and compare our results in order to conclude which ones of the indexes is more volatile. The OMX Nordic list indexis quiet new(2002)and reorganized as late as October 2006. The current value is now about 300 and no options do exist. In current work we are also interested in estimation of the Heston model(SVmodel), which is popular in financial world and can be used in option pricing in the future. The results of our investigations show that Large Cap Index is more volatile then Middle and Small Cap Indexes.

In this thesis the GARCH models are applied to evaluate financial options and futures. In the first application, the GARCH models in parsimonious form are studied for pricing the S&P500 options. Unlike previous studies that focus on developed formulation, the results indicate that simplified models provide effective performance and it is the simple GARCH model that yields the least valuation error. To our consideration, examining model possessing simplification is of practical importance because model estimation becomes readily accessible through available econometric software, which circumvent programming barriers in implementing alternative one’s own pricing methods. The second application consider the component GARCH models for currency option pricing. The valuation results favour the component formulations particularly in the pricing of long term contracts. Volatility modelling results indicate that the return-volatility relationship is symmetric in the long run, but over the short term asymmetry also arises in the EURUSD and GBPUSD exchange rates. The third application evaluates canola futures in Canada in relation to spot market price. Results confirm the cointegrating relationship with threshold corresponding to transaction and adjustment cost. And it is the futures market that adjusts actively to price disparities but in the meantime there is volatility spillover from futures to the spot market. Overall, our empirical assessments indicate the importance of the time varying volatility and the improvements achieved in option pricing and futures evaluation. We believe the present study’s analysis provides useful suggestions and further guidance to practitioners and investors for the pricing and trading in the equity and foreign exchange markets, also to the market agents to better evaluate price uncertainty in order to guard against adverse price changes.

Changing in variance or volatility with time can be modeled as deterministic by using autoregressive conditional heteroscedastic (ARCH) type models, or as stochastic by using stochastic volatility (SV) models. This study compares these two kinds of models which are estimated on Turkish / USA exchange rate data. First, a GARCH(1,1) model is fitted to the data by using the package E-views and then a Bayesian estimation procedure is used for estimating an appropriate SV model with the help of Ox code. In order to compare these models, the LR test statistic calculated for non-nested hypotheses is obtained.

The purpose of this thesis is to investigate the financial volatility dynamics through the GARCH modelling framework. We use univariate and multivariate GARCH-type models enriched with long memory, asymmetries and power transformations. We study the financial time series volatility and co-volatility taking into account the structural breaks detected and focusing on the effects of the corresponding financial crisis events. We conclude to provide a complete framework for the analysis of volatility with major policy implications and benefits for the current risk management practices. We first investigate the volume-volatility link for different investor categories and orders, around the Asian crisis applying a univariate dual long memory model. Our analysis suggests that the behaviour of volatility depends upon volume, but also that the nature of this dependence varies with time and the source of volume. We further apply the vector AR-DCC-FIAPARCH and the UEDCC-AGARCH models to several stock indices daily returns, taking into account the structural breaks of the time series linked to major economic events including crisis shocks We find significant cross effects, time-varying shock and volatility spillovers, time-varying persistence in the conditional variances, as well as long range volatility dependence, asymmetric volatility response to positive and negative shocks and the power of returns that best fits the volatility pattern. We observe higher dynamic correlations of the stock markets after a crisis event, which means increased contagion effects between the markets, a continuous herding investors’ behaviour, as the in-crisis correlations remain high, and a higher level of correlations during the recent financial crisis than during the Asian. Finally, we study the High-frEquency-bAsed VolatilitY (HEAVY) models that combine daily returns with realised volatility. We enrich the HEAVY equations through the HYAPARCH formulation to propose the HYDAP-HEAVY (HYperbolic Double Asymmetric Power) and provide a complete framework to analyse the volatility process.

This thesis consists of eight studies that cover topics in the increasingly influential field of futures- commodities, macroeconomic volatility and financial development. Chapter 2 considers the case of Argentina and provides a first thorough examination of the timing of the Argentine debacle. By applying a group of econometric tests for structural breaks on a range of GDP growth series over a period from 1886 to 2003 we conclude that there are two key dates in Argentina's economic history (1918 and 1948) that need to be inspected closely in order to further our understanding of the Argentine debacle. Chapters 3 and 4 investigated the time-varying link between financial development and economic growth. By employing the logistic smooth transition framework to annual data for Brazil covering the period 1890-2003 we found that financial development has a mixed (either positive or negative) time- varying effect on growth, which depends on trade openness thresholds. We also find a positive impact of trade openness on growth while a mainly negative one for the various political instability measures. Chapter 5 studied the convergence properties of inflation rates among the countries of the European Monetary Union over the period 1980-2013. By applying recently developed panel unit root/stationarity tests overall we are able to accept the stationarity hypothesis. Similarly, results from the univariate testing procedure indicated a mixed evidence in favour of convergence. Hence next we employ a clustering algorithm in the context of multivariate stationarity tests and we statistically detect three absolute convergence clubs in the pre-euro period, which consist of early accession countries. We also detect two separate clusters of early accession countries in the post-1997 period. For the rest of the countries/cases we find evidence of divergent behaviour. For robustness check we additionally employ a pairwise convergence Bayesian framework, which broadly confirms our findings. Finally, we show that in the presence of volatility spillovers and structural breaks time-varying persistence will be transmitted from the conditional variance to the conditional mean. Chapter 6 focuses on the negative consequences that the five years of austerity (2010-2014) imposed on the Greek economy and the society in general. To achieve that goal we summarize the views of three renowned economists, namely Paul De Grauwe, Paul Krugman and Joseph Stiglitz on the eurozone crisis as well as the Greek case. In support of their claims we provide solid evidence of the dramatic effects that the restrictive policies had on Greece. Chapter 7 analyzes the properties of inflation rates and their volatilities among five European countries over a period 1960-2003. Unlike to previous studies we investigate whether or not the infl ation rate and its volatility of each individual country displayed time-varying characteristics. By applying various power ARCH processes with structural breaks and with or without in-mean effects the results indicated that the conditional means, variances as well as the in-mean effect displayed time-varying behaviour. We also show that for France, Italy and Netherlands the in-mean effect is positive, whereas that of Austria and Denmark is negative. Chapter 8 examines the stochastic properties of different commodity time series during the recent fi nancial and EU sovereign debt crisis (1997-2013). By employing the Bai-Perron method we detect five breaks for each of the commodity returns (both in the mean and in the variance). The majority of the breaks are closely associated with the two aforementioned crises. Having obtained the breaks we estimated the power ARCH models for each commodity allowing the conditional means and variances to switch across the breakpoints. The results indicate overall that there is a time-varying behaviour of the conditional mean and variance parameters in the case of grains, energies and softs. In contrast, metals and soya complex show time-varying characteristics only in the conditional variance. Finally, conducting a forecasting analysis using spectral techniques (in both mapped and unmapped data) we find that the prices of corn remained almost stable while for wheat, heating oil, wti and orange juice the prices decreased further, though slightly. In the case of natural gas, coffee and sugar overall the prices experienced significant defl ationary pressures. As far as the prices of oats, platinum, rbob, cocoa, soybean, soymeal and soyoil is concerned, they showed an upward trend. Chapter 9 examines the effect of health and military expenditures, trade openness and political instability on output growth. By employing a pooled generalised least squares method for 19 NATO countries from 1993 to 2010 we fi nd that there is a negative impact of health and military expenditures, and political instability on economic growth whereas that of trade openness is positive.

Since the Bretton Woods System collapsed, the volatility of the exchange rate return has been an important and concerned issue in financial domain. The purpose of this paper is to investigate the empirical relevance of stricture breaks for the volatility of the exchange rate return, and we use both in-sample and out-of-sample tests. GARCH(1,1) Model is considered to be the representative quantitative method for analyzing the volatility of asset returns, as a result, we picked GARCH(1,1) as natural benchmarks in this article. In addition, we cogitated the structure breaks in this paper, and used ICSS(Iterated Cumulative Sums of Squares) algorithm to test the points of structural breaks. The results of empirical analysis show that there are significant evidences of structural breaks in the unconditional variance for six of eight US exchange rate return series, which implying unstable GARCH processes for these exchange rates. We also find those competing models that accommodating structural breaks will have higher predictive ability. Pooling forecasts from different models that allow for structural breaks in volatility appears to offer a reliable method for improving volatility forecast accuracy given the uncertainty surrounding the timing and size of the structural breaks.

Βασικός στόχος αυτής τη εργασίας είναι να παρουσιάσει με λεπτομερή και τεκμηριωμένο τρόπο την διαδικασία που ακολουθεί ένας χρηματοοικονομικός αναλυτής έτσι ώστε να προσδιορίσει την σχέση απόδοσης και κινδύνου κάποιων χρεογράφων με απώτερο σκοπό να καταλήξει σε ορθολογικά συμπεράσματα που μπορούν να τον οδηγήσουν στις βέλτιστες αποφάσεις. Οι αποφάσεις αυτές θα αφορούν την δόμηση ενός βέλτιστου χαρτοφυλακίου χρεογράφων το οποίο για δεδομένο κίνδυνο θα αποφέρει την μέγιστη αναμενόμενη απόδοση η αντίστροφα με δεδομένη την επιθυμητή απόδοση θα ενέχει το ελάχιστο ρίσκο . Η χρήση του απλού γραμμικού υποδείγματος , της μεθόδου ελαχίστων τετραγώνων (OLS) , των διαστημάτων εμπιστοσύνης και της στατιστικής συμπερασματολογίας είναι κάποιες από τις μεθόδους που θα εφαρμόσουμε για να προσδιορίσουμε με ακρίβεια την σχέση απόδοσης και κινδύνου χρεογράφων των οποίων έχουμε επιλέξει για τις εφαρμογές μας . Οι διαταράξεις των υποθέσεων του απλού γραμμικού υποδείγματος , όπως η αυτοσυσχέτιση και η ετεροσκεδαστικότητα είναι επίσης αντικείμενα προς εξέταση ,παράγοντες οι οποίοι αλλοιώνουν τις οικονομετρικές εκτιμήσεις της μεθόδου των ελαχίστων τετραγώνων και πρέπει να άρονται από τον αναλυτή, έτσι ώστε να καταλήγει η ανάλυση και η έρευνα των χρηματοοικονομικών εφαρμογών σε αξιόπιστες εκτιμήσεις . Ιδίως στην αντιμετώπιση της ετεροσκεδαστικότητας, η χρήση των μοντέλων ARCH/GARCH, μπορεί να μας οδηγήσει στο ζητούμενο ,το οποίο είναι η εκτίμηση και η πρόβλεψη του μελλοντικού κινδύνου αγοράς ενός χρεογράφου όπως η μετοχή . / The basic goal of this paper is to present in an analytic and trustworthy way, the process that a financial analyst follows so as to evaluate the relationship between risk and return of stocks. This kind of process will lead the analyst to rational conclusions and effective decisions which concern the structure of optimal portfolios of stocks. The optimal portfolio structure offers a maximum expected return if the risk is known and vice versa (minimum risk when the return is known).The use of the simple linear model, least square method and statistical conclusion function, are some of the methods that will help us to measure the relationship between risk and return of the stocks that we have chose to use for our applications. The disorders of the simple linear model assumptions, autocorrelation and heteroscedasticity, are parameters who are making the estimations of least squares method spurious. The analyst has to detect these problems so as the analysis and research of financial applications to conclude rational and effective estimations.Specialy in coping with heteroscedasticity, the use of ARCH/GARCH models can lead us to the objective, the estimation and forecast of the future risk of the stock being studied.

The statements that include sufficient detail to identify the probability distributions of future prices are asset price dynamics. In this research, using the empirical methods that could explain the historical prices and discuss about how prices change we investigate various important characteristics of the dynamics of asset pricing. The volatility changes can explain very important facts about the asset returns. Volatility could gauge the variability of prices over time. In order to do the volatility modelling we use the conditional heteroskedasticitc models. One of the most powerful tools to do so is using the idea of autoregressive conditional heteroskedastic process or ARCH models, which fill the gap in both academic and practical literature. In this work we detect the asymmetric volatility effect and investigate long memory properties in volatility in Canadian stock market index, using daily data from 1979 through 2015. On one hand, we show that there is an asymmetry in the equity market index. This is an important indication of how information impacts the market. On the other hand, we investigate for the long-range dependency in volatility and discuss how the shocks are persistence. By using the long memory-GARCH models, we not only take care of both short and long memory, but also we compute the d parameter that stands for the fractional decay of the series. By considering the breaks in our dataset, we compare our findings on different conditions to find the most suitable fit. We present the best fit for GARCH, EGARCH, APARCH, GJR-GARCH, FIGARCH, FIAPARCH, and FIEGARCH models.