The VaR Models for financial derivatives : The case of Taiwan Top50 Tracker Fund

• Main Authors: Sheng-Yuan Chuang, 莊盛元
• Other Authors: Rwei-Ju Chuang
• Format: Others
• Language: zh-TW
• Published: 2006
• Online Access: http://ndltd.ncl.edu.tw/handle/43359299717320796232

碩士 === 輔仁大學 === 應用統計學研究所 === 94 === The main goal for this research is to evaluate the performance of three different risk models for Taiwan Top50 Tracker Fund which type is Exchange Traded Fund (ETF). The result might be useful and helpful for investors or financial companies to control their risk on ETF investment. Therefore, in this work, two main goals have been set. First, according to the historical data of Taiwan Top50 Tracker Fund, the Value at Risk models are estimated using three moving-window size in combination with three different models. Using the results as the baseline solution, the appropriate VaR model for ETF will be developed from comparison. Second, the trend of ETF can be determined as three different periods, increasing, decreasing and steady. The appropriate VaR models for marketing volatility will be worth to develop and evaluate. The results will offer flexible and forceful methods for administrators to control their risk at investment. Results illustrate the differences between the three methods and highlight the influence of moving-window size on the analysis. There are two findings from this work. First, the appropriate window size suggested for further study is 65 days. It is more sensitive to detect the volatility of VaR of ETF. The other, a comparison of the VaR models of three different trend periods, it is hard to examine the appropriate model for different trend of ETF. However, the administrators can inference the results for further study to detect and diversify the potential risk of ETF.