Computational Statistics

, Volume 24, Issue 3, pp 533–550 | Cite as

The convergence of estimators based on heuristics: theory and application to a GARCH model

Original Paper

Abstract

Econometric theory describes estimators and their properties, e.g., the convergence of maximum likelihood estimators. However, it is ignored that often the estimators cannot be computed using standard tools, e.g., due to multiple local optima. Then, optimization heuristics might be helpful. The additional random component of heuristics might be analyzed together with the econometric model. A formal framework is proposed for the analysis of the joint convergence of estimator and stochastic optimization algorithm. In an application to a GARCH model, actual rates of convergence are estimated by simulation. The overall quality of the estimates improves compared to conventional approaches.

Keywords

GARCH Threshold accepting Optimization heuristics Convergence 

References

  1. Bollerslev T, Ghysels E (1996) Periodic autoregressive conditional heteroscedasticity. J Bus Econ Stat 14(2): 139–151CrossRefGoogle Scholar
  2. Bond D, Harrison MJ, O’Brien EJ (2005) Investigating nonlinearity: a note on the estimation of Hamilton’s random field regression model. Studies in Nonlinear Dynamics and Econometrics, Article 2Google Scholar
  3. Brooks C, Burke SP, Persand G (2001) Benchmark and the accuracy of GARCH model estimation. Int J Forecast 17: 45–56CrossRefGoogle Scholar
  4. Clements MP, Krolzig H-M (1998) A comparison of the forecast performance of Markov-switching and threshold autoregressive models. Econom J 1: C47–C75CrossRefGoogle Scholar
  5. Dorsey B, Mayer WJ (1995) Genetic algorithms for estimation problems with multiple optima, nondifferentiability and other irregular features. J Bus Econ Stat 13: 53–66CrossRefGoogle Scholar
  6. Dueck G, Scheuer T (1990) Threshold accepting: a general purpose algorithm appearing superior to simulated annealing. J Comput Phys 90: 161–175MATHCrossRefMathSciNetGoogle Scholar
  7. Fang K-T, Maringer D, Tang Y, Winker P (2005) Lower bounds and stochastic optimization algorithms for uniform designs with three or four levels. Math Comput 75(254): 859–878CrossRefMathSciNetGoogle Scholar
  8. Fiorentini G, Calzolari G, Panattoni L (1996) Analytic derivatives and the computation of GARCH estimates. J Appl Econom 11(4): 399–417CrossRefGoogle Scholar
  9. Fitzenberger B (1997) A guide to censored quantile regressions. In: Maddala GS, Rao CR (eds) Handbook of statistics, vol 15: Robust inference. Elsevier, Amsterdam, pp 405–437Google Scholar
  10. Fitzenberger B, Winker P (2007) Improving the computation of censored quantile regressions. Comput Stat Data Anal 52(1): 88–108MATHCrossRefMathSciNetGoogle Scholar
  11. Hamilton JD (2001) A parametric approach to flexible nonlinear inference. Econometrica 69(3): 537–573MATHCrossRefMathSciNetGoogle Scholar
  12. Hamilton JD (2005) Comment on investigating nonlinearity. Studies in Nonlinear Dynamics and Econometrics, Article 3Google Scholar
  13. Herwartz H (2004) Conditional heteroskedasticity. In: Lütkepohl H, Krätzig M (eds) Applied time series econometrics. Cambridge University Press, Cambridge, pp 197–221Google Scholar
  14. Ho MS, Sørensen BE (1996) Finding cointegration rank in high dimensional systems using the Johansen test: an illustration using data based Monte Carlo simulations. Rev Econ Stat 78(4): 726–732CrossRefGoogle Scholar
  15. Maringer D (2005) Portfolio management with heuristic optimization. Springer, BerlinMATHGoogle Scholar
  16. Maringer D, Meyer M (2008) Smooth transition autoregressive models—new approaches to the model selection problem. Studies in Nonlinear Dynamics and Econometrics 12(1), Article 5 (2008)Google Scholar
  17. McCullough B, Renfro CG (1999) Benchmarks and software standards: a case study for GARCH procedures. Comput Econ Social Meas 25: 59–71Google Scholar
  18. McCullough BD, Vinod HD (1999) The numerical reliability of econometric software. J Econ Lit 38: 633–665Google Scholar
  19. McCullough BD, Wilson B (1999) On the accuracy of statistical procedures in Microsoft Excel 97. Comput Stat Data Anal 31(1): 27–37MATHCrossRefGoogle Scholar
  20. McCullough BD, Wilson B (2002) On the accuracy of statistical procedures in Microsoft Excel 2000 and Excel XP. Comput Stat Data Anal 40(4): 713–721MATHCrossRefMathSciNetGoogle Scholar
  21. McCullough BD, Wilson B (2005) On the accuracy of statistical procedures in Microsoft Excel 2003. Comput Stat Data Anal 49(4): 1244–1252MATHCrossRefMathSciNetGoogle Scholar
  22. Winker P (2000) Optimized multivariate lag structure selection. Comput Econ 16: 87–103MATHCrossRefGoogle Scholar
  23. Winker P (2001) Optimization heuristics in econometrics: applications of threshold accepting. Wiley, ChichesterMATHGoogle Scholar
  24. Winker P (2006) The stochastics of threshold accepting: analysis of an application to the uniform design problem. In: Rizzi A, Vichi M (eds) COMPSTAT 2006, Proceedings in computational statistics. Physica, Heidelberg, pp 495–503CrossRefGoogle Scholar
  25. Winker P, Maringer D (2004) Optimal lag structure selection in VAR and VEC models. In: Welfe A (eds) New Directions in macromodeling. Elsevier, Amsterdam, pp 213–234Google Scholar
  26. Winker P, Fang K-T (1997) Application of threshold accepting to the evaluation of the discrepancy of a set of points. SIAM J Numer Anal 34: 2028–2042MATHCrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag 2009

Authors and Affiliations

  1. 1.Statistics and EconometricsUniversity of GiessenGiessenGermany
  2. 2.Computational Management ScienceUniversity of BaselBaselSwitzerland

Personalised recommendations