Invariance of the first difference in ARFIMA models
| 详细信息 | 推荐本文 | |
- 作者：Barbara P. Olbermann (1) barbarap@pucrs.br
S铆lvia R. C. Lopes (2) slopes@mat.ufrgs.br
Vald茅rio A. Reisen (3) - 关键词：Non ; stationary processes ; Long memory ; Estimation ; Invariance
- 刊名：Computational Statistics
- 出版时间：December 2006
- 出版年：2006
- 期刊代码：pc577_0943-4062
- 类别：mat
- 卷：21
- 期：3-4
- 页码：445-461
- 数据来源：sp
摘要
A desirable property for an estimator of the fractional ARFIMA parameter is to be first difference invariant. This paper investigates the effects on the fractional parameter estimator in nonstationary ARFIMA(p,d,q) processes before and after applying a first difference. We consider semiparametric and parametric approaches for estimating d. The study is based on a Monte Carlo simulation for different sample sizes. The Brazilian exchange rate series is given as an application of the methodology.