Markov Bridges, Bisection and Variance Reduction

  • Søren Asmussen
  • Asger Hobolth
Conference paper
Part of the Springer Proceedings in Mathematics & Statistics book series (PROMS, volume 23)


Time-continuous Markov jump processes are popular modeling tools in disciplines ranging from computational finance and operations research to human genetics and genomics. The data is often sampled at discrete points in time, and it can be useful to simulate sample paths between the datapoints. In this paper we firstly consider the problem of generating sample paths from a continuous-time Markov chain conditioned on the endpoints using a new algorithm based on the idea of bisection. Secondly we study the potentials of the bisection algorithm for variance reduction. In particular, examples are presented where the methods of stratification, importance sampling and quasi Monte Carlo are investigated.


Sample Path Importance Sampling Variance Reduction Rate Matrix Continuous Time Markov Chain 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Asmussen, S. (2003). Applied Probability and Queues (2nd ed.). Springer-Verlag.Google Scholar
  2. 2.
    Asmussen, S. and Glynn, P.W. (2007). Stochastic Simulation. Algorithms and Analysis Springer-Verlag.Google Scholar
  3. 3.
    Asmussen, S. and Hobolth, A. (2008). Bisection ideas in end-point conditioned Markov process simulation. In Proceedings of the 7th International Workshop on Rare Event Simulation (G. Rubino and B. Tuffin, eds.), 121–130. Rennes, France.Google Scholar
  4. 4.
    Avramidis, A.N., L’Ecuyer, P. and Tremblay, P.-A. (2003) Efficient simulation of gamma and variance-gamma processes. In Proceedings of the 2003 Winter Simulation Conference (S. Chick et al., eds.).Google Scholar
  5. 5.
    Beskos, A., Papaspiliopoulos,O. and Roberts, G.O. (2006) Retrospective exact simulation of diffusion sample paths with applications. Bernoulli 12, 1077–1098.Google Scholar
  6. 6.
    Beskos, A., Papaspiliopoulos, O. and Roberts, G.O. (2008a). A factorisation of diffusion measure and finite sample path constructions. Methodol. Comput. Appl. Probab. 10, 85–104Google Scholar
  7. 7.
    Beskos, A., Roberts, G.O., Stuart, A. and Voss, J. (2008b) MCMC methods for diffusion bridges. Stoch. Dyn. 8, 319–350.Google Scholar
  8. 8.
    Bladt, M., Gonzales, A. and Lauritzen, S.L. (2003). The estimation of phase-type related functionals using Markov chain Monte Carlo. Scand. Act. J. 4, 280–300.Google Scholar
  9. 9.
    Bladt, M. and Sørensen, M. (2009) Simple simulation of diffusion bridges with application to likelihood inference for diffusions.
  10. 10.
    Caflish, R.E. and Moskowitz, B. (1995) Modified Monte Carlo methods using quasi-random sequences. In Monte Carlo and Quasi-Monte Carlo Methods in Scientific Computing (H. Niederreiter and P.J.-S. Shine, eds.). Lecture Notes in Statistics 106, 1–16. Springer-VerlagGoogle Scholar
  11. 11.
    Caflish, R.E., Morokoff, W. and Owen, A.B. (1997). Valuation of mortgage-backed securities using Brownian bridges to reduce effective dimension. J. Comput. Finance 1, 27–46.Google Scholar
  12. 12.
    de Koning, A.P.J., Gu, J. and Pollock, D.D. (2010). Rapid Likelihood Analysis on Large Phylogenies Using Partial Sampling of Substitution Histories. Mol Biol Evol 27, 249–265.Google Scholar
  13. 13.
    Duret, L. (2008). Neutral theory: The null hypothesis of molecular evolution. Nature Education 1(1).Google Scholar
  14. 14.
    Ewens, W.J. and Grant, G.R. (2001). Statistical methods in Bioinformatics. Springer-Verlag.Google Scholar
  15. 15.
    Fearnhead, P. and Sherlock, C. (2006). An exact Gibbs sampler for the Markov-modulated Poisson process. J.R. Statist. Soc. B 68, 767–784.Google Scholar
  16. 16.
    Felsenstein, J. (1981). Evolutionary trees from DNA sequences: a maximum likelihood approach. J. Mol. Evol. 17, 368–376.Google Scholar
  17. 17.
    Felsenstein, J. (2004). Inferring Phylogenies. Sinauer Associates, Inc.Google Scholar
  18. 18.
    Fitzsimmons, P., Pitman, J. and Yor, M. (1992) Markovian bridges: construction, Palm interpretation and splicing. In Seminar on Stochastic Processes. Progress in Probability 32, 101–134.Google Scholar
  19. 19.
    Hobolth, A. (2008) A Markov chain Monte Carlo expectation maximization algorithm for statistical analysis of DNA sequence evolution with neighbour-dependent substitution rates. Journal of Computational and Graphical Statistics 17, 138–164.Google Scholar
  20. 20.
    Hobolth, A. and Stone, E.A. (2009). Efficient simulation from finite-state, continuous-time Markov chains with incomplete observations. Ann. Appl. Statist. 3, 1204–1231.Google Scholar
  21. 21.
    Hwang, D.G. and Green, P. (2004). Bayesian Markov chain Monte Carlo sequence analysis reveals varying neutral substitution patterns in mammalian evolution. PNAS, 101, 13994–14001.Google Scholar
  22. 22.
    Jensen, J. L. and Pedersen, A.-M. K. (2000). Probabilistic models of DNA sequence evolution with context dependent rates of substitution. Adv. Appl. Prob., 32, 499–517.Google Scholar
  23. 23.
    Kimura, M. (1980). A simple method for estimating evolutionary rates of base substitutions through comparative studies of nucleotide sequences. J. Mol. Evol. 16, 111–120.Google Scholar
  24. 24.
    Leobacher, G. (2006) Stratified sampling and quasi-Monte Carlo simulation of Lévy processes. Monte Carlo Methods and Applications 12, 231–238.Google Scholar
  25. 25.
    Metzner, P., Dittmer, E., Jahnke, T. and Schútte, C. (2007). Generator estimation of Markov jump processes. Journal of Computational Physics 227, 353–375.Google Scholar
  26. 26.
    Moler, C. and van Loan, C. (2003). Nineteen dubious ways to compute the exponential of a matrix, twenty-five years later. SIAM Review 45, 3–49.Google Scholar
  27. 27.
    Moskowitz, B. and Caflish, R.E. (1996) Smoothness and dimension reduction in quasi-Monte Carlo methods. Journal of Mathematical and Computer Modeling 23, 37–54.Google Scholar
  28. 28.
    Nielsen, R. (2002). Mapping mutations on phylogenies. Syst. Biol., 51, 729–739.Google Scholar
  29. 29.
    Ribeiro, C. and Webber, N. (2003) Valuing path-dependent options in the variance-gamma model by Monte Carlo with a gamma bridge. J. Comput. Finance 7, 81–100.Google Scholar
  30. 30.
    Ribeiro, C. and Webber, N. (2006) Correction for simulation bias in Monte Carlo methods to value exotic options in models driven by Lévy processes. Appl. Math. Finance 13, 333–352.Google Scholar
  31. 31.
    Roberts, G.O. and Stramer, O. (2001) On inference for partially observed nonlinear diffusion processes using Metropolis-Hastings algorithms. Biometrika 88, 603–621.Google Scholar
  32. 32.
    Siepel, A., Pollard, K.S. and Haussler, D. (2006). New methods for detecting lineage-specific selection. Proceedings of the 10th International Conference on Research in Computational Molecular Biology (RECOMB), 190–205.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  1. 1.Department of Mathematical SciencesAarhus UniversityAarhusDenmark
  2. 2.Bioinformatics Research CenterAarhus UniversityArhusDenmark

Personalised recommendations