Return to search

Parameter estimation in interest rate models using Gaussian radial basis functions

When modeling interest rates, using strong formulations of underlying differential equations is prone to bad numerical approximations and high computational costs, due to close to non-smoothness in the probability density function of the interest rate. To circumvent these problems, a weak formulation of the Fokker–Planck equation using Gaussian radial basis functions is suggested. This approach is used in a parameter estimation process for two interest rate models: the Vasicek model and the Cox–Ingersoll–Ross model. In this thesis, such an approach is shown to yield good numerical approximations at low computational costs.

Identiferoai:union.ndltd.org:UPSALLA1/oai:DiVA.org:uu-527839
Date January 2024
Creatorsvon Sydow, Gustaf
PublisherUppsala universitet, Sannolikhetsteori och kombinatorik
Source SetsDiVA Archive at Upsalla University
LanguageEnglish
Detected LanguageEnglish
TypeStudent thesis, info:eu-repo/semantics/bachelorThesis, text
Formatapplication/pdf
Rightsinfo:eu-repo/semantics/openAccess
RelationU.U.D.M. project report ; 2024:4

Page generated in 0.0022 seconds