Semiparametric diffusion estimation and application to a stock market index

The analysis of diffusion processes in financial models is crucially dependent on the form of the drift and diffusion coefficient functions. A methodology is proposed for estimating and testing coefficient functions for ergodic diffusions that are not directly observable. It is based on semiparametric and nonparametric estimates. The testing is performed via the wild bootstrap resampling technique. The method is illustrated on S&P 500 index data.

MoreLess

Year of publication:	2001
Authors:	Härdle, Wolfgang ; Kleinow, Torsten ; Korostelev, Alexander P. ; Logeay, Camille ; Platen, Eckhard
Publisher:	Berlin : Humboldt University of Berlin, Interdisciplinary Research Project 373: Quantification and Simulation of Economic Processes
Subject:	Identification, Bootstrap, Diffusion, Continuous-time financial models, Semiparametric methods, Kernel smoothing

More details

Series:	SFB 373 Discussion Paper ; 2001,24
Type of publication:	Book / Working Paper
Type of publication (narrower categories):	Working Paper
Language:	English
Other identifiers:	724876618 [GVK] hdl:10419/62746 [Handle] RePEc:zbw:sfb373:200124 [RePEc]
Classification:	C51 - Model Construction and Estimation ; C52 - Model Evaluation and Testing ; G22 - Insurance; Insurance Companies
Source:	EconStor

Persistent link: https://ebvufind01.dmz1.zbw.eu/10010310398