Finance Dissertation 21071809 UWE Dissertation submitted in partial fulfillment of the Requirement for the MSc in Finance FINANCE DISSERTATION ON FORECASTING THE VALUE AT RISK (VaR) FOR THE STOCK MARK[.]
Finance Dissertation 21071809 UWE Dissertation submitted in partial fulfillment of the Requirement for the MSc in Finance FINANCE DISSERTATION ON FORECASTING THE VALUE AT RISK (VaR) FOR THE STOCK MARKET IN VIETNAM Nguyen Ha Phuong ID No: 21071809 Intake Supervisor: Dr Le Hai Trung September 2022 Tai ngay!!! Ban co the xoa dong chu nay!!! 17014126289251000000 Finance Dissertation 21071809 UWE Acknowledgement First and foremost, I would like to express my sincerely appreciation to my supervisor - Dr Le Hai Trung, who always give helpful advice as well as ready to answer any related question With his enthusiasm, motivation and patience, my dissertation can be completed on time with few obstacles Without Dr Le Hai Trung, I cannot imagine how I can finish this research I also think Dr Le Hai Trung is the best supervisor for me to this study during my undergraduate time Besides, I also want to send my thanks to Dr Roberto, who taught me the Quantitative Research Method as well as Dr Pham Manh Hung, who taught me Final Project subject They provided me a lot of skills, knowledge and supported me on the way of completing my research I also want to show my gratefulness to Banking Academy of Vietnam as well as University of the West of England for providing me usefulness subject, great studies environment, and opportunities to this dissertation Lastly, thanks to my family for trusting and giving me the opportunity to study in such a professional and international environment They also always support and listen to my difficulties during this time i Finance Dissertation 21071809 UWE Abstract This research assesses methodologies for forecasting value at risk, or VaR, applied to the Vietnamese market via the stock market channel To forecast the VaR value with 99% confidence in real time, three distinct techniques utilising non-parametric (Historical Simulation method) and parametric method (GARCH model) are evaluated The VaR forecasts are backtested with the stipulation that the proper forecast should provide percentile coverage and independence amongst forecasts The findings of backtesting the VaR forecast from the models indicate that only the GARCH-SGED model with the estimation of the conditional probability distribution under the assumption of a non-normal distribution predicts a nonnormal distribution for the VN-Index return ratio The precision of VaR predictions is unparalleled This indicates that conventional models that assume a normal distribution for the VN-Index returns will generate VaR estimates that are lower than the real market risk This study's findings can be applied to the application of risk-bearing value forecasting models in calculating minimum capital requirements for market risk at banks within the context of Basel II accord treaty application ii Finance Dissertation 21071809 UWE List of Abbreviations CPI Consumer Price Index FDI Foreign Direct Investment GDP Gross Domestic Product HNX Hanoi Stock Exchange HNXI HNX-Index HOSE Ho Chi Minh Stock Exchange SBV State Bank of Vietnam SSC State Securities Commission UPCOM Unlisted Public Companies VaR Value at Risk VNI VN-Index VNIAS VN All Share Index VSE Vietnam Stock Exchange iii Finance Dissertation 21071809 UWE List of Tables Table Page Table 2.1: Non-rejection regions for number of backtesting exceptions X 22 Table 2.2: Exception table with expected number of exceptions 24 Table 4.1: Descriptive statistic for VN-Index 37 Table 5.1: Backtesting results 40 iv Finance Dissertation 21071809 UWE List of Figures Figure Page Figure 2.1: Calculation of VaR from the probability distribution of the gain in portfolio value Figure 1.2: Calculation of VaR from the probability distribution of the loss in portfolio value Figure 2.3: Probability distribution for gain in portfolio value during time T 10 Figure 2.4: t- distributions with different degrees of freedom "df" displaying the convergence to the normal distribution as df to infinity 16 Figure 2.5: t-VaR at different degrees of freedom 16 Figure 2.6: The total Vietnamese stock market size from 2000 to 2020 30 Figure 2.7: Number of enterprises listed for HOSE and HNX from 2015 to 2022 31 Figure 2.8: Market capitalization in Vietnamese stock market from 2015 to 2022 32 Figure 2.9: Indices for stock market in Vietnam 34 Figure 5.1: Movement of VN-Index 39 Figure 5.2: VaR1% forecast for VN-Index earnings ratio for the models under consideration 40 v Finance Dissertation 21071809 UWE Table of Contents Acknowledgement i Abstract ii List of Abbreviations iii List of Tables iv List of Figures v Chapter 1: Introduction 1.1 Rationale 1.2 Research Gap 1.3 Objectives 1.4 Scope of the Research 1.5 Research Questions 1.6 Research Structure Chapter 2: Literature Review 2.1 Definition of Value at Risk (VaR) 2.2 The Development of the VaR 10 2.3 VaR Forecasting Methods 13 2.3.1 Non-Parametric Method: Historical Simulation Model 14 2.3.2 Parametric Method: GARCH Models 15 2.3.2.1 ARCH Model 17 2.3.2.2 GARCH Model 18 2.4 Back-testing VaR 20 vi Finance Dissertation 21071809 UWE 2.4.1 Unconditional Coverage Back-testing: Kupiec Test 22 2.4.2 Coverage Back-testing: Christoffersen Test 23 Chapter 3: An Overview of the Stock Market in Vietnam 25 3.1 Main Feature of Stock Market in Vietnam 25 3.1.1 Definition 25 3.1.2 Functions of Vietnam's Stock Market and Its Participants 26 3.1.3 Principles of Operation in the Stock Market in Vietnam 28 3.2 Current Situation Vietnam's Stock Market 29 Chapter 4: Data Collection and Methodology 36 4.1 Research Methodology 36 4.2 Data Description 37 4.2.1 Data Collection 37 4.2.2 Descriptive Statistics 37 Chapter 5: Results 39 5.1 Movement of Timeseries Dataset VN-Index 39 5.2 Backtesting Results 40 Chapter 6: Conclusion 43 REFERENCES .45 vii Finance Dissertation 21071809 UWE FORECASTING THE VALUE AT RISK (VaR) FOR THE STOCK MARKET IN VIETNAM Chapter 1: Introduction 1.1 Rationale Together with the banking system, the stock market is an important financial source for the economy Vietnam is currently one of the most dynamic emerging countries in the world with a rapidly growing economy and stock market (World Bank, 2022) Compared to other stock markets in the world, the Vietnamese stock exchange (VSE) is rather young The first trading of the Ho Chi Minh Stock Exchange (HOSE) was started on 28 July 2000, with only two securities, and that of the Hanoi Stock Exchange (HNX) was on 14 July 2005 (Truong and Friday, 2021) Until now, the stock market of Vietnam is still made up of two principal stock exchanges: the Ho Chi Minh Stock Exchange (HOSE) listing companies with charter capital above VND 120 billion; and the Hanoi Stock Exchange (HNX), listing companies with above VND 30 billion (State Securities Commission of Vietnam, 2012) The number of listed companies increased from in 2000 to 750 in 2021 (Kokalari, 2021) The stock market of Vietnam has turned from a frontier market into an emerging market Market capitalization increased by almost three times during the 2014–2020 period, from USD 52.43 billion to USD 186.01 billion (The World Bank, 2022) Volatility in the equity market, which is a fundamental concept in the discipline of finance, has been seen as a measure of the uncertainty of investment’s rate of return As a proxy of risk, modelling and forecasting stock market volatility have become a concerned subject of numerous empirical and theoretical contributions over past decades VaR is a popular and widely used tool to measure and control market risk so forecasting and modelling stock volatility through estimating value at risk (VaR) are crucial Finance Dissertation 21071809 UWE inputs for pricing derivatives and for trading and hedging strategies Furthermore, the extreme volatility could disrupt the smooth functioning of the financial system and lead to structural or regulatory changes Therefore, it is important to understand the behaviour of return volatility Stock markets around the world have, over the last two decades, experienced large fluctuations and swings, which considerably increased the risk of investment in stock portfolios During the financial crisis of 2007-2009, world stock markets witnessed a fall in their asset price and exhibited volatility (Nguyen, 2020) The VSE had also experienced several difficulties, and the bubble burst Both the VN index (HOSE) and the HNX index (HNX) declined by nearly 70% in 2008, one of the biggest losses ever seen in any of the world stock markets Since 2009, the VSE has been still unstable, with high volatility Moreover, the coronavirus disease (COVID-19), which commenced at the end of 2019, has had a very serious impact on many fields of social and economic life of all countries across the world in unprecedented ways On 11 March 2020, the WHO (World Health Organization) declared it a pandemic, and up to 28 December 2020, there were 222 countries affected with over 79 million confirmed cases and nearly million deaths (WHO, 2022) COVID19 has caused substantial negative effects on the performance of stock markets around the world (Zhang et al 2020; Alfaro et al 2020; Al-Awadhi et al 2020; Lin al 2020; Ahmar and Val 2020; Baker et al 2020; Ding et al 2020) Directive No 16/CT-TTg implemented a nationwide lockdown, spanning the period April 2020 to 15 April 2020, to curb community transmission of the virus The Vietnamese stock market is no exception, and the VN-index declined dramatically in the first three months of the year (Giang and Yap, 2020) from 31 December 2019 to 30 March 2020 Market capitalization declined 37.4 billion USD in absolute value, or 28% in relative value in this period As COVID-19 hits the market, it will cause economic disruption, delays in investment decisions, and decline in business profits, which result in a slide in stock prices (Ashraf, 2020) As a result, forecasting VaR for the stock market is a need for all