Comparison of approaches to estimation of transition matrix for the terrorist threat Markov model

  • 1 University of Defence, Brno, Czech Republic


Markovian models are often used in modelling a time development of random phenomena. When modelling real world scenarios it is reasonable to assume that the respective phenomena may not be time homogeneous. Based on the sociological and security research, it can be assumed that there is a link between a destabilisation of a society of a given geographical region and the acts of terrorism. This link is utilised in construction of a model for description of the intensity of a terrorist threat based on given determinants/indicators of societal stability. The model is based on the theory of discrete non-homogeneous Markov chains. The theory of generalised linear models (GLMs) is used in the estimation of the probabilities of the categorised level of the terrorist threat. In the contribution the use of different estimates of the categorised level of terrorist threat probabilities is studied. The estimates are determined by GLMs with different input parameters. The influence of the resulting estimate on the transition matrix of the non-homogeneous Markov chain is assessed. Additionally, a real world example utilising the data from Global Terrorism Database of University of Maryland and Organisation for Economical Cooperation and Development is presented.



  1. Jarrow, R.A., Lando, D., Turnbull, S.M., A Markov model for the term structure of credit risk spreads. The Review of Financial Studies 10 (2), 1997, 481–523.
  2. Altman, E. I. and Kao, D. The implications of corporate bond rating drift. Financial Analysts Journal, 48(3), 1992, 64–75.
  3. Carty, L. V. and Fons, J. S. Measuring Changes in Corporate Credit Quality, Journal of Fixed Income, 4(1), 1994, 27–41.
  4. Nickell, P., Perraudin, W. and Varotto, S. Stability of rating transitions. Journal of Banking & Finance, 24(1–2), 2000, 203–227.
  5. Koopman, S. J. and Lucas, A. Business and default cycles for credit risk. Journal of Applied Econometrics, 20(2), 2005, 311–323.
  6. Gavalas, D. and Syriopoulos, T. Bank Credit Risk Management and Rating Migration Analysis on the Business Cycle. International Journal of Financial Studies, 2(1), 2014, 122–143.
  7. Svoboda, I. and Hrbata, M. Extremism and Terrorism as Destabilizing Factors of Society, Vojenské rozhledy, 23 (55), N. 1, p., 2014, 33 - 41 (In Czech)
  8. Tejkal, M. and Michálek, J. Markov Model for Description of Intensity of Terrorist Threat. Abstracts of XXXII International Conference Problems of Decision Making under Uncertainties (PDMU-2018) , July 3-9, 2018, Prague, Czech Republic.
  9. Resnick, S. I., Adventures in stochastic processes, Boston: Birkhäuser, 1992.
  10. Agresti, A., Categorical data analysis, 3rd ed. Hoboken, NJ: Wiley, 2013.
  11. Fahrmeir, L. and Tutz G. Multivariate statistical modelling based on generalized linear models. New York, Springer-Verlag, 1994.

Article full text

Download PDF