Value at Risk Model Used to Stock Prices Prediction

The focus of the author is the Value at Risk model which is currently often adopted as the risk analysis model, particularly in banking and insurance. Following the model principle characteristics, the Value at Risk is economically interpreted. Attention is paid to the distinct features of three sub-methods: historical simulation, the Monte Carlo method and variance and covariance method. A row of empirical studies of the practical application of these methods are provided. The objective of the paper is the application of the Value at Risk model on shares from the SPAD segment of the Prague Stock Exchange between 2009 and 2011. A corresponding reliability interval, hold time, historical period and other essential parameters related to the sub-methods are gradually defined and chosen. By using historical values of stocks and shares, diverse statistical indicators are calculated. The diversified Values at Risk of the sub-methods are benchmarked against the non-diversified ones. The results show that any loss related to the non-diversified Value at Risk is always higher among the three methods than a loss related to a diversified Value at Risk. We can expect – with selected probability – a drop in the value of the portfolio which differs depending on which method is adopted based on recent share developments. The methodology is further benchmarked against other methodologies used in other papers applying the Value at Risk model. The message of this paper lies in the unique selection of applied methods, risk factors and the stock market. The methodology allows us to evaluate the risk level for investments in shares in a specific way, which will be appreciated by numerous financial entities when making an investment decision.