Event Date
Speaker: Sebastian Kühnert, Visiting Assistant Professor, Dept of Statistics, UC Davis
Title: An operator-level GARCH model
Abstract: Conditional heteroskedastic processes are commonly described by the GARCH model, which has been extensively studied in the uni- and multivariate case, and recently also in function spaces. This paper extends the concept of the functional GARCH model, which has been defined exclusively on function spaces in the point-wise sense. The GARCH model in this article is defined in general, separable Hilbert spaces, and the GARCH equations consider the entire functions. Sufficient conditions for strictly stationary solutions, finite moments and weak dependence are derived and sufficient and necessary conditions for weak stationarity are discussed. In addition, consistent Yule-Walker estimates with explicit convergence rates are established for the finite-dimensional projections of the GARCH parameters and also for their entire representation. Finally, the usefulness of the proposed model is demonstrated through a simulation study and a real data example.
Speaker's Website (links to Google site): https://scholar.google.com/citations?hl=en&user=x9w0ntcAAAAJ
Seminar Date/Time: Thursday May 30, at 3:10pm (refreshments at 2:45pm)*
*There is a second seminar immediately following this one.
Location: MSB 1147, Colloquium Room