Abstract
In this artilce, we develop a monitoring procedure for an early detection of distributional changes in autoregressive models. We design the monitoring procedure based on residuals since the test based on the observations is inappropriate. We verify that under regularity conditions, the stopping rule designed to detect changes behaves asymptotically the same as that in iid samples. Simulation results are provided for illustration.
| Original language | English |
|---|---|
| Pages (from-to) | 2969-2982 |
| Number of pages | 14 |
| Journal | Communications in Statistics - Theory and Methods |
| Volume | 38 |
| Issue number | 16-17 |
| DOIs | |
| State | Published - 2009.01 |
Keywords
- Autoregressive models
- Distributional changes
- Monitoring parameter changes
- Residual-based sequential empirical process
- Strong approximation
Fingerprint
Dive into the research topics of 'Monitoring distributional changes in autoregressive models'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver