Journal article
Temporal Aggregation of Stationary and Non-stationary Continuous-Time Processes
Scandinavian journal of statistics, Vol.32(4), pp.583-597
Received February 2004, in final form February 2005
12/2005
DOI: 10.1111/j.1467-9469.2005.00455.x
Abstract
We study the autocorrelation structure of aggregates from a continuous-time process. The underlying continuous-time process or some of its higher derivative is assumed to be a stationary continuous-time auto-regressive fractionally integrated moving-average (CARFIMA) process with Hurst parameter H. We derive closed-form expressions for the limiting autocorrelation function and the normalized spectral density of the aggregates, as the extent of aggregation increases to infinity. The limiting model of the aggregates, after appropriate number of differencing, is shown to be some functional of the standard fractional Brownian motion with the same Hurst parameter of the continuous-time process from which the aggregates are measured. These results are then used to assess the loss of forecasting efficiency due to aggregation. © Board of the Foundation of the Scandinavian Journal of Statistics 2005.
Details
- Title: Subtitle
- Temporal Aggregation of Stationary and Non-stationary Continuous-Time Processes
- Creators
- HENGHSIU Tsai - Academia SinicaK. S Chan - University of Iowa
- Resource Type
- Journal article
- Publication Details
- Scandinavian journal of statistics, Vol.32(4), pp.583-597
- Edition
- Received February 2004, in final form February 2005
- Publisher
- Blackwell Publishing Ltd
- DOI
- 10.1111/j.1467-9469.2005.00455.x
- ISSN
- 0303-6898
- eISSN
- 1467-9469
- Number of pages
- 15
- Language
- English
- Date published
- 12/2005
- Academic Unit
- Statistics and Actuarial Science; Radiology
- Record Identifier
- 9984257633702771
Metrics
2 Record Views