Skip to main content
SpringerLink
Log in

A structured variational learning approach for switching latent factor models

  • Original Paper
  • Published:
AStA Advances in Statistical Analysis Aims and scope Submit manuscript

Abstract

A data-driven approach for modeling volatility dynamics and co-movements in financial markets is introduced. Special emphasis is given to multivariate conditionally heteroscedastic factor models in which the volatilities of the latent factors depend on their past values, and the parameters are driven by regime switching in a latent state variable. We propose an innovative indirect estimation method based on the generalized EM algorithm principle combined with a structured variational approach that can handle models with large cross-sectional dimensions. Extensive Monte Carlo simulations and preliminary experiments with financial data show promising results.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Akaike, H. (1974) A new look at the statististical identification model. IEEE Transactions on Automatic Control 19, 716–723

    Article  MATH  MathSciNet  Google Scholar 

  2. Anderson, B.O., Moore, J.B. (1979) Optimal Filtering. Prentice Hall, Englewood Cliffs, NJ

    MATH  Google Scholar 

  3. Barber, D., Wiegerinck, W. (1999) Tractable variational structures for approximating graphical models. In: Kaerns, M.S., Solla, S.A., Cohn, D.A. (eds.) Advances in neural information processing systems. 183–189, MIT Press, Cambridge, MA

    Google Scholar 

  4. Bera, A.K., Jarque, C.M. (1982) Model specification tests: A simultaneous approach. Journal of Econometrics 20, 59–82

    Article  MATH  MathSciNet  Google Scholar 

  5. Campbell, J.Y., Lettau, M., Malkiel, B.G., Xu, Y. (2001) Have individual stocks become more volatile? An empirical exploration of idiosyncratic risk. Journal of Finance 56, 1–43

    Google Scholar 

  6. Demos, A., Sentana, E. (1998) An EM algorithm for conditionally heteroscedastic factor models. Journal of Business & Economic Statistics 16, 357–361

    Article  Google Scholar 

  7. Dempster, A., Laird, N., Rubin, D. (1977) Maximum Likelihood from incomplete data via the EM algorithm. Journal of Royal Statistical Society Series B 39, 1–38

    MATH  MathSciNet  Google Scholar 

  8. Diebold, F., Nerlove, M. (1988) The dynamics of exchange rate volatility: A multivariate latent factor ARCH model. Journal of Applied Econometrics 4, 1–22

    Article  Google Scholar 

  9. El-Hay, T., Friedman, N. (2001) Incorporating expressive graphical models in variational approximations: Chain-graphs and hidden variables. Breese, J.S., Koller, D. (eds.) Proc. Seventeenth Conf. on Uncertainty in Artificial Intelligence (UAI). University of Washington, Seattle 136–143

  10. Engle, R., Ng, V.K., Rothschild, M. (1990) Asset pricing with a Factor-ARCH covariance structure: Empirical estimates for treasury bills. Journal of Econometrics 45, 213–237

    Article  Google Scholar 

  11. Engle, R., Ng, V.K., Rothschild, M. (1992) A multi-dynamic factor model for stock returns. Journal of Econometrics 52, 245–266

    Article  Google Scholar 

  12. Engle, R., Susmel, R. (1993) Common volatility in international equity markets. Journal of Business & Economic Statistics 11, 369–380

    Article  Google Scholar 

  13. French, K., Schwert, G., Stambaugh, R. (1987) Expected stock returns and volatility. Journal of Financial Economics 19, 3–30

    Article  Google Scholar 

  14. Ghahramani, Z., Jordan, M.I. (1997) Factorial Hidden Markov Models. Machine Learning 29, 245–274

    Article  MATH  Google Scholar 

  15. Geweke, J.F., Zhou, G. (1996) Measuring the pricing error of the arbitrage pricing theory. The Review of Financial Studies 9, 557–587

    Article  Google Scholar 

  16. Gupta, A.K. (1952) Estimation of the mean and standard deviation of a normal population from a censored sample. Biometrika 39, 260–273

    MATH  MathSciNet  Google Scholar 

  17. Harvey, A., Ruiz, E., Sentana, E. (1992) Unobserved component time series models with ARCH disturbances. Journal of Econometrics 52, 129–157

    Article  Google Scholar 

  18. Jaakkola, T.S., Jordan, M.I. (1996) Computing upper and lower bounds on likelihoods in intractable networks. Horvitz, E., Jensen, F.V. (eds.) Proceedings of the Twelth Annual Conference on Uncertainty in Artificial Intelligence. Reed College, Portland 340–348

  19. Jaakkola, T.S., Jordan, M.I. (1998) Improving the mean field approximation via the use of mixture distributions. Jordan, M.I. (ed.) Learning in graphical models. Kluwer Academic Publishers, Norwell, MA

    Google Scholar 

  20. Jones, C.S. (2001) Extracting factors from heteroskedastic asset returns. Journal of Financial Economics 62, 293–325

    Article  Google Scholar 

  21. Jordan, M.I., Ghahramani, Z., Jaakkola, T.S., Saul, L.K. (1998) An introduction to variational methods for graphical models. Machine Learning 37, 183–233

    Article  Google Scholar 

  22. Juang, B.H., Rabiner, L.R. (1985) A probabilistic distance measure for hidden Markov models. AT&T Technical Journal 64, 391–408

    MathSciNet  Google Scholar 

  23. King, M., Sentana, E., Wadhwani, S. (1994) Volatility and links between national stock markets. Econometrica 62, 901–933

    Article  MATH  Google Scholar 

  24. Lawrence, N.D., Bishop, C.M., Jordan, M.I. (1998) Mixture representations for inference and learning in Boltzmann machines. In: Kaufmann, M. (ed.) Proceedings of the 14th Annual Conference on Uncertainty in Artificial Intelligence (UAI), pp. 320–332. San Francisco, CA

  25. Lin, W. (1992) Alternative estimators for factor GARCH models: a Monte Carlo comparaison. Journal of Applied Econometrics 7, 259–279

    Article  Google Scholar 

  26. Ljung, G., Box, G. (1978) On a measure of lack of fit in time series models. Biometrika 67, 297–303

    Article  Google Scholar 

  27. Saidane, M., Lavergne, C. (2006a) A generalized pseudo-Bayesian EM algorithm for switching dynamic factor analysis. International Journal of Computer Science and Network Security 6, 30–37

    Google Scholar 

  28. Saidane, M., Lavergne, C. (2006b) On factorial HMMs for time series in finance. The Kyoto Economic Review 75, 63–90

    Google Scholar 

  29. Saidane, M., Lavergne, C. (2006c) Learning and inference in mixed-state conditionally heteroscedastic factor models using viterbi approximation – lecture notes in Computer Science. LNCS 3994, Part IV, 372–379. Springer-Verlag, Berlin Heidelberg

  30. Schwarz, G. (1978) Estimating the dimension of a model. Annals of Statistics 6, 461–464

    MATH  MathSciNet  Google Scholar 

  31. Schwert, G.W. (1989) Why does stock market volatility change over time? Journal of Finance 44, 1115–1153

    Article  Google Scholar 

  32. Schwert, G.W., Seguin, P.J. (1990) Heteroskedasticity in stock returns. Journal of Finance 45, 1129–1155

    Article  Google Scholar 

  33. Sentana, E. (1995) Quadratic ARCH models. Review of Economic Studies 62, 639–661

    Article  MATH  Google Scholar 

  34. Shapiro, S.S., Francia, R.S. (1972) An approximate analysis of variance test for normality. Journal of the American Statistical Association 67, 215–216

    Article  Google Scholar 

  35. Sharpe, W.F. (1963) A simplified model for portfolio analysis. Management Science 9, 277–293

    Article  Google Scholar 

  36. Stephens, M.A. (1975) Asymptotic properties for covariance matrices of order statistics. Biometrika 62, 23–28

    Article  MATH  MathSciNet  Google Scholar 

  37. Wainwright, M., Jaakkola, T., Willsky, A. (2002) A new class of upper bounds on the log partition function. IEEE Transactions on Information Theory 51, 2313–2335

    Article  MathSciNet  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Institut de Mathématiques et de Modélisation de Montpellier, Université Montpellier II, Place Eugène Bataillon CC, 051, 34095, Montpellier, France

    Mohamed Saidane

  2. Département Mathématiques et Informatique Appliqués, Université Paul-Valéry Montpellier III, Route de Mende, 34199, Montpellier Cedex 5, France

    Christian Lavergne

Authors
  1. Mohamed Saidane
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Christian Lavergne
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mohamed Saidane.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Saidane, M., Lavergne, C. A structured variational learning approach for switching latent factor models . AStA 91, 245–268 (2007). https://doi.org/10.1007/s10182-007-0031-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10182-007-0031-4

Keywords

Search

Navigation