In this thesis we are concerned with estimation of clustering probabilities for univariate heavy tailed time series. We employ functional convergence of a bivariate tail empirical process to conclude asymptotic normality of an estimator of the clustering probabilities. Theoretical results are illustrated by simulation studies.
| Identifer | oai:union.ndltd.org:uottawa.ca/oai:ruor.uottawa.ca:10393/30906 |
| Date | January 2014 |
| Creators | Dimy Anguima Ibondzi, Herve |
| Contributors | Kulik, Rafal |
| Publisher | Université d'Ottawa / University of Ottawa |
| Source Sets | Université d’Ottawa |
| Language | English |
| Detected Language | English |
| Type | Thesis |
Page generated in 0.0018 seconds