The Impacts of Low-return Distribution on GARCH Effects and Technical Indices

• Main Authors: Ching-Wang Chen, 陳旌王
• Other Authors: none
• Format: Others
• Language: zh-TW
• Published: 2002
• Online Access: http://ndltd.ncl.edu.tw/handle/07902877594971726291

碩士 === 中原大學 === 國際貿易研究所 === 90 === As the result of financial globalization and industrial changes, Taiwan’s stock market has become more volatility. This paper explores the problems of testing and estimating GARCH models with particular on the impact of data return, firm size and trading volume. This paper also uses variance of stock’s return which estimates by GARCH model to test the impacts on Technical Indices. We conduct our investigation by analysing 695 of daily return data on 169 Taiwan’s companies. Referring to the empirical results, GARCH model testing and estimation are impacted by the degree of censoring, firm and trading volume. Specifically, our analysis produces four major findings. First, we find that most Taiwan’s companies have GARCH effect. GARCH (1,1) model is a good method to solve heteroscedasticity. Second, we find that low trading volume and high censoring lead to a higher persistence of GARCH effects in the estimated models. Third, we find that MACD is a good technical indictor. High censoring stock that uses MACD technical indictor of month can obtain more return, but low censoring stock that uses MACD technical indictor of week can obtain more return. Forth, we find that low censoring stock has more risk than high censoring stock.