Augmented Half‐Life Estimation Based on High‐Frequency Data |
| |
| Authors: | Mao‐Lung Huang Shu‐Yi Liao Kuo‐Chin Lin |
| |
| Institution: | 1. Department of Hotel Management, Tainan University of Technology, Taiwan;2. Department of Applied Economics, National Chung Hsing University, Taichung, Taiwan;3. Department of Business Administration, Tainan University of Technology, Taiwan |
| |
| Abstract: | Half‐life estimation has been widely used to evaluate the speed of mean reversion for various economic and financial variables. However, half‐life estimation for the same variable are often different due to the length of the annual time series data used in alternative studies. To solve this issue, this paper extends the ARMA model and derives the half‐life estimation formula for high‐frequency monthly data. Our results indicate that half‐life estimation using short‐period monthly data is an effective approximation for that using long‐period annual data. Furthermore, by applying high‐frequency data, the required effective sample size can be reduced by at least 40% at the 95% confidence level. Copyright © 2015 John Wiley & Sons, Ltd. |
| |
| Keywords: | half‐life high frequency data ARMA lag length sunspots |
|
|
