Journal of the Korean Data and Information Science Society
- 제14권3호
- /
- Pages.471-479
- /
- 2003
- /
- 1598-9402(pISSN)
Moving Averages Based on Robust Statistical Analysis
초록
Moving averages are the most popular statistics in analyzing time-series data like stock indices. However, moving averages are quite sensitive to unusual observations. In other words, they are not robust against unusual observations. We introduce the moving averages in terms of an M-estimator, and show how we can take advantages of using the proposed moving averages in fitting the data more than usual moving averages.