Computational Statistics

, Volume 30, Issue 2, pp 517–537

Semiparametric stochastic volatility modelling using penalized splines

  • Roland Langrock
  • Théo Michelot
  • Alexander Sohn
  • Thomas Kneib
Original Paper

DOI: 10.1007/s00180-014-0547-5

Cite this article as:
Langrock, R., Michelot, T., Sohn, A. et al. Comput Stat (2015) 30: 517. doi:10.1007/s00180-014-0547-5


Stochastic volatility (SV) models mimic many of the stylized facts attributed to time series of asset returns, while maintaining conceptual simplicity. The commonly made assumption of conditionally normally distributed or Student-t-distributed returns, given the volatility, has however been questioned. In this manuscript, we introduce a novel maximum penalized likelihood approach for estimating the conditional distribution in an SV model in a nonparametric way, thus avoiding any potentially critical assumptions on the shape. The considered framework exploits the strengths both of the hidden Markov model machinery and of penalized B-splines, and constitutes a powerful alternative to recently developed Bayesian approaches to semiparametric SV modelling. We demonstrate the feasibility of the approach in a simulation study before outlining its potential in applications to three series of returns on stocks and one series of stock index returns.


B-splines Cross-validation Forward algorithm   Hidden Markov model Numerical integration Penalized likelihood 

Supplementary material

180_2014_547_MOESM1_ESM.r (12 kb)
Supplementary material 1 (R 12 KB)
180_2014_547_MOESM2_ESM.cpp (1 kb)
Supplementary material 2 (cpp 1 KB)

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • Roland Langrock
    • 1
  • Théo Michelot
    • 2
  • Alexander Sohn
    • 3
  • Thomas Kneib
    • 3
  1. 1.University of St AndrewsSt AndrewsUK
  2. 2.INSA de RouenRouenFrance
  3. 3.Georg August University of GöttingenGöttingenGermany

Personalised recommendations