Calendar effects in Taiwan stock market: A data snooping study

• Main Authors: Ming-Chieh Chen, 陳明傑
• Other Authors: Chin-Sheng Huang
• Format: Others
• Language: zh-TW
• Published: 2005
• Online Access: http://ndltd.ncl.edu.tw/handle/11123239476084254287

碩士 === 國立雲林科技大學 === 財務金融系碩士班 === 93 === This study mainly checks whether calendar effects exists in Taiwan stock market. To rule out data-snooping biases, this paper utilizes bootstrap procedure to resample and test the calendar effects. However, the existing literatures show that calendar effects could bring the value of economic information content in the stock market. There appears to be very substantial calendar effects of systematic abnormal stock returns related to the day of the week, the week of the month, the month of the year, holidays, and so forth. In this paper we use 34 years of daily data of Taiwan stock market index and use White''s（2000） Bootstrap Reality Check, to test whether calendar rules can perform better than of the benchmark of always being in the market. We find that althougth nominal p-value for individual calendar rules are extremely significant. But, after ruling out data-snooping biases, the performance of the best calendar rule can not be superior to the benchmarket and no calendar rules can be used to profit in the market by investors. This result supports Fama’s（1970）weak form efficiency market hypothesis of Taiwan stock market.