Model selection for stock prices data

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

The geometric Brownian motion (GBM) is very popular in modeling the dynamics of stock prices. However, the constant volatility assumption is questionable and many models with nonconstant volatility have been developed. In the papers [7,12] the authors introduce a regime switching process where in each regime the process is driven by GBM and the change in regime is defined by the crossing of a threshold. In this paper we used Akaike's and Bayesian information criteria to show that the GBM with regimes provides a better fit than the GBM. We also perform a forecasting comparison of the models for two selected companies.

Original languageEnglish
Pages (from-to)2977-2987
Number of pages11
JournalJournal of Applied Statistics
Volume43
Issue number16
DOIs
Publication statusPublished - 9 Dec 2016

Keywords

  • AIC
  • BIC
  • geometric Brownian motion
  • maximum likelihood estimator
  • regimes

Fingerprint Dive into the research topics of 'Model selection for stock prices data'. Together they form a unique fingerprint.

Cite this