The aim of the thesis is to reveal the relationship between stock indices and GDP of selected countries. The theoretical part explains the concepts of financial mar-kets, the essence of a functioning of public limited companies and earlier studies dealing with this theme are also included. The practical part is focused on an ac-tual relationship between the variables, both in terms of its existence, its strength and direction. To reveal the relationship between variables and its strength, the correlation analysis is used. Then In case of direction of this relationship a multivariate time series analysis is used in a form of the VAR model using Granger causality.

The indebtedness of Swedish households has more than doubled in the last ten decades despite the implementation of a mortgage ceiling and stricter amortization requirements. This study takes form to investigate how it is possible that debt related to housing is rising while new regulations against it has been set and how housing prices continues to increase when lending is supposed to be harder.This analysis estimates whether there are indications of an existing price bubble in the housing market of Stockholm. It is done by testing fundamental economic factors to the price index of housing in Stockholm, to see if they support the price development. If the analysis shows that housing prices cannot be predicted by the fundamental economic factors, it is possible that the price is a self-running series1 which could be an indicator of a price bubble. If fundamental factors that are being used as control variables seem to follow the same trend as the price development of the housing market, the speculation of price bubble will be rejected.

Value-at-Risk (VaR) model fails to predict financial risk accurately especially during financial crises. This is mainly due to the model’s inability to calibrate new market information and the fact that the risk measure is characterised by poor tail risk quantification. An alternative approach which comprises of the Expected Shortfall measure and the Lognormal Jump-Diffusion (LJD) model has been developed to address the aforementioned shortcomings of VaR. This model is called the Simulated-Expected-Shortfall (SES) model. The Maximum Likelihood Estimation (MLE) approach is used in determining the parameters of the LJD model since it’s more reliable and authenticable when compared to other nonconventional parameters estimation approaches mentioned in other literature studies. These parameters are then plugged into the LJD model, which is simulated multiple times in generating the new loss dataset used in the developed model. This SES model is statistically conservative when compared to peers which means it’s more reliable in predicting financial risk especially during a financial crisis. / Statistics / M.Sc. (Statistics)

為了控制健保醫療費用的成長速度，我國全民健保自2002年開始全面實施總額預算制，在總額預算制下醫療費用總額泱定於事前協商之每人醫療費用成長率，因此為提供一合理客觀之成長率協商依據，本研究建構一醫療費用成長時間序列隨機模型，並佐以總體經濟模型，利用模擬結果推估未來15年部分總體經濟變數數值及醫療費用成長率。 利用常用以預測總體經濟相關變數之VAR MODEL，本研究檢測發現平均國民所得、醫療物價指數、消費者物價指數及失業率之成長率，明顯受到自身及其他三個變數之前四期數值之影響。 此外，根據本研究之研究結果，醫療費用占國民所得比重成長率除了受到季節因素影響以外，與其自身前期及人口老化指數呈正向關係，與醫療物價指數則呈反向關係，同時具備MA(1)之時間趨勢。 關鍵字：全民健康保險、醫療費用、隨機模型、VAR MODEL、模擬。

M. Comm. / Although there has been several work done on monetary policy and inflation in South Africa, this dissertation is intended to add and expand on the existing literature on the subject with data dating back to 1970. The dissertation was inspired by recent international research that has indentified that a large Bayesian VAR model normally performs better than the normal SVAR model. Given that there has already been differing conclusions in literature on whether interest rates are effective as a tool to control inflation, there is therefore an opportunity to assess monetary policy using a different and more robust modelling framework. The choice of a sample is informed by the fact that prior to inflation targeting and within the period under consideration; interest rates remained a core factor in monetary policy management. Some of the literature will be discussed in detail in chapter 2. This dissertation will introduce the large BVAR model with 14 variables in the South African economy. In comparison, the SVAR model suffers from the curse of dimensionality that is eliminated by using more variables with the Large Bayesian VAR with the response functions of all 14 variables. The objective is therefore to determine whether interest rate changes in South Africa have a meaningful and desired effect on inflation. A substantial amount of recent literature was done within the environment of inflation targeting; however, our study intends to measure more the responsiveness of interest rates and other macro variables to monetary policy. The period of inflation targeting in South Africa provides more useful data and evidence on the responsiveness of the macro variables given the direct policy approach it represents versus the previous regime and hence it is covered in more detail in the dissertation. We also assess, in the process, the main drivers behind inflation in South Africa, in an effort to establish whether the country suffers from cost- push or demandpush. The type of inflation should also assist in providing recommendations on the appropriate response to inflation.

Nous analysons dans cette thèse le pouvoir de contribution du marché d’options à l’efficience informationnelle et à la stabilité du marché des actions françaises cotées sur Euronext-LIFFE pour la période 1996-2006.Nous nous proposons, en outre, de définir dans quelle mesure la fusion d’Euronext avec le Liffe en 2002 et les conditions macroéconomiques de 1996-2006, influencent cette contribution.L’étude de l’introduction d’options sur les caractéristiques des actions met en évidence, (i) l’absence d’impact aussi bien sur la volatilité que sur le risque systématique des actions mesuré par le bêta, (ii) un effet prix négatif qui reste statistiquement non significatif dans la majorité des séances, (iii) une hausse significative du volume, (iv) une baisse de la fourchette de prix. La modélisation VAR montre que l’introduction de l’option ne renforce l’ajustement du volume par rapport à la volatilité des actions significativement qu’au seuil de 10%. En outre, la proportion des agents informés sur le marché des actions n’est pas plus importante à la suite de la création d’options.La modélisation Log-ACD (Autoregressive Conditionnel Duration) augmentée par l’introduction de la liquidité comme variable explicative ne détecte aucun effet de l’introduction de l’option sur le renfort informationnel des actions.Par ailleurs, notre étude met en évidence que l’objectif du marché d’options est la couverture (respectivement la spéculation et/ou arbitrage) en période de forte volatilité (respectivement faible). La fusion d’Euronext avec le Liffe en 2002 n’introduit pas de changement significatif au niveau de l’amélioration du processus d’ajustement des prix aux nouvelles. Le résultat global de l’absence d’effet de l’introduction de l’option sur les actions, s’explique par le trading fondé, actuellement en France, sur la volatilité. Ce qui amenuise le pouvoir prédictif des options. / We investigate the impact of option listing on the underlying stock dynamics and the informational efficiency of the stock market, using data from the French Euronext Paris stock market about new option listing that occurred over the period 1996 – 2006. We take into account the implementation of a new trading system after the Euronext merger with the Liffe market in 2002 and the macroeconomic changes over the period.Considering different characteristics of stocks, we observe (i) no effect on both volatility and systematic risk measured by the beta, (ii) a negative price effect, although insignificant at the majority of times, (iii) a significant rise in the volume and, finally (iv), a significant decrease in the spread bid-ask. By estimating a VAR model, we highlight a better adjustment to new information, observable jointly through contemporaneous and delayed relations between volume and volatility. However, when decomposing volatility into the contributions of informed and non-informed agents, we cannot document any migration of informed traders to the underlying stock market after option listing. We confirm the absence of impact of option listing on the underlying stock pricing efficiency by examining the stock price duration dynamics, using a modified Log-ACD model that accounts for liquidity captured by trade size.On the other hand, we show that in high volatility periods (low volatility periods), the option market plays a hedging role (speculation and/or arbitrage). The implementation of the new trading system after the Euronext merger with the Liffe market in 2002 appears to have no significant impact on the underlying stock. The global result about the absence impact of option listing is justified by the underlying stock’s volatility-driven trading. These strategies disturb the connection between option and underlying stock markets and the predictive power of option prices.

The aim of the thesis is to verify the interdependence of stock markets with the development of the national economies of the V4 countries and on basis of the established links, to assess possible forecasting of the future development of GDP and the development of V4 stock markets. Literary overview of the diploma thesis describes the economic development of the V4 countries with a focus on the eco-nomic indicator of GDP, the critism of the GDP indicator and its possible alternati-ves measuring the efficiency of the economy. In addition, there are described indi-vial stock exchanges of V4 countries, theory of efficient markets together with possible anomalies in the financial markets. The last part of the literky review contains previously Publisher studies dealing with the issue. The work itself is dividend into main parts, namely the correlation analysis and the compilation of VAR models according to which the direction of the relationship will be tested within Granger causality.

The diploma thesis focuses on the development of the Czech labour market in the period of the CNB monetary interventions that took place in 2013-2017. Within the VAR models, the causal relationship between the labour market indicators and the GDP growth is verified. The delayed effect of the change in GDP on the labour market indicators was found. The thesis also pays attention to the trend models of the selected time series. Within them the presence of the structural break indicating the start of using CNB foreign exchange interventions was detected. In conclusion the possible solutions of the long-term unemployment of disadvantaged groups in the labour market are presented.

Asset pricing implications of a DSGE model with recursive preferences and nominal rigidities. I study jointly macroeconomic dynamics and asset prices implied by a production economy featuring nominal price rigidities and Epstein-Zin (1989) preferences. Using a reasonable calibration, the macroeconomic DSGE model is consistent with a number of stylized facts observed in financial markets like the equity premium, a negative real term spread, a positive nominal term spread and the predictability of stock returns, without compromising the model's ability to fit key macroeconomic variables. The interest rate smoothing in the monetary policy rule helps generate a low risk-free rate volatility which has been difficult to achieve for standard real business cycle models where monetary policy is neutral. In an application, I show that the model provides a framework for analyzing monetary policy interventions and the associated effects on asset prices and the real economy. Macroeconomic news and the stock market: Evidence from the eurozone. This paper is an empirical study of excess return behavior in the stock market in the euro area around days when important macroeconomic news about inflation, unemployment or interest rates are scheduled for announcement. I identify state dependence such that equity risk premia on announcement days are significantly higher when the interests rates are in the vicinity of the zero lower bound. Moreover, I provide evidence that for the whole sample period, the average excess returns in the eurozone are only higher on days when FOMC announcements are scheduled for release. However, this result vanishes in a low interest rate regime. Finally, I document that the European stock market does not command a premium for scheduled announcements by the European Central Bank (ECB). The impact of ECB monetary policy surprises on the German stock market. We examine the impact of ECB monetary policy surprises on German excess stock returns and the possible reasons for such a response. First, we conduct an event study to asses the impact of conventional and unconventional monetary policy on stock returns. Second, within the VAR framework of Campbell and Ammer (1993), we decompose excess stock returns into news regarding expected excess returns, future dividends and future real interest rates. We measure conventional monetary policy shocks using futures markets data. Our main findings are that the overall variation in German excess stock returns mainly reflects revisions in expectations about dividends and that the stock market response to monetary policy shocks is dependent on the prevailing interest rate regime. In periods of negative real interest rates, a surprise monetary tightening leads to a decrease in excess stock returns. The channels behind this response are news about higher expected excess returns and lower future dividends.

Value-at-Risk (VaR) model fails to predict financial risk accurately especially during financial crises. This is mainly due to the model’s inability to calibrate new market information and the fact that the risk measure is characterised by poor tail risk quantification. An alternative approach which comprises of the Expected Shortfall measure and the Lognormal Jump-Diffusion (LJD) model has been developed to address the aforementioned shortcomings of VaR. This model is called the Simulated-Expected-Shortfall (SES) model. The Maximum Likelihood Estimation (MLE) approach is used in determining the parameters of the LJD model since it’s more reliable and authenticable when compared to other nonconventional parameters estimation approaches mentioned in other literature studies. These parameters are then plugged into the LJD model, which is simulated multiple times in generating the new loss dataset used in the developed model. This SES model is statistically conservative when compared to peers which means it’s more reliable in predicting financial risk especially during a financial crisis. / Statistics / M.Sc. (Statistics)