The Annals of Applied Statistics

Bayesian inference for double Pareto lognormal queues

Pepa Ramirez-Cobo, Rosa E. Lillo, Simon Wilson, and Michael P. Wiper

Full-text: Open access

Abstract

In this article we describe a method for carrying out Bayesian estimation for the double Pareto lognormal (dPlN) distribution which has been proposed as a model for heavy-tailed phenomena. We apply our approach to estimate the dPlN / M / 1 and M / dPlN / 1 queueing systems. These systems cannot be analyzed using standard techniques due to the fact that the dPlN distribution does not possess a Laplace transform in closed form. This difficulty is overcome using some recent approximations for the Laplace transform of the interarrival distribution for the Pareto / M / 1 system. Our procedure is illustrated with applications in internet traffic analysis and risk theory.

Article information

Source
Ann. Appl. Stat., Volume 4, Number 3 (2010), 1533-1557.

Dates
First available in Project Euclid: 18 October 2010

Permanent link to this document
https://projecteuclid.org/euclid.aoas/1287409385

Digital Object Identifier
doi:10.1214/10-AOAS336

Mathematical Reviews number (MathSciNet)
MR2758340

Zentralblatt MATH identifier
1202.62041

Keywords
Heavy tails Laplace transform approximation methods queueing systems Bayesian methods

Citation

Ramirez-Cobo, Pepa; Lillo, Rosa E.; Wilson, Simon; Wiper, Michael P. Bayesian inference for double Pareto lognormal queues. Ann. Appl. Stat. 4 (2010), no. 3, 1533--1557. doi:10.1214/10-AOAS336. https://projecteuclid.org/euclid.aoas/1287409385


Export citation

References

  • Adler, R., Feldman, R. and Taqqu, M. T. (1999). A Practical Guide to Heavy Tails: Statistical Techniques and Applications. Birkhäuser, Boston.
  • Armero, C. and Bayarri, M. J. (1994). Bayesian prediction in M / M / 1 queues. Queueing Syst. 15 401–417.
  • Ausín, M. C., Lillo, R. E. and Wiper, M. P. (2007). Bayesian control of the number of servers in a GI / M / c queueing system. J. Statist. Plann. Inference 137 3043–3057.
  • Beirlant, J., Goegebeur, Y., Verlaak, R. and Vynckier, P. (1998). Burr regression and portfolio segmentation. Insurance Math. Econom. 23 231–250.
  • Beirlant, J. and Goegebeur, Y. (2003). Regression with response distributions of Pareto-type. Computat. Statist. Data Anal. 42 595–619.
  • Beirlant, J., Goegebeur, Y., Segers, J. and Teugels, J. (2004). Statistics of Extremes: Theory and Applications. Wiley, New York.
  • Box, G. and Tiao, G. (1973). Bayesian Inference in Statistical Analysis. Wiley, New York.
  • Embrechts, P., Klüppelberg, C. and Mikosch, T. (1997). Modelling Extremal Events for Insurance and Finance. Springer, Heidelberg.
  • Fischer, M. and Knepley, J. (1977). A numerical solution for some computational problems occurring in queueing theory. In Algorithmic Methods in Probability, Studies in Management Science 271–285. North-Holland, Amsterdam.
  • Gross, D. and Harris, C. M. (1998). Fundamentals of Queueing Theory. Wiley, New York.
  • Harris, C. M. and Marchal, W. G. (1998). Distribution estimation using Laplace transforms. INFORMS J. Comput. 10 448–458.
  • Harris, C. M., Brill, P. H. and Fischer, M. J. (2000). Internet-type queues with power-tailed interarrival times and computational methods for their analysis. INFORMS J. Comput. 12 261–271.
  • Leland, W. E. and Wilson, D. V. (1991). High time-resolution measurement and analysis of LAN traffic: Implications for LAN interconnection. In Proc. IEEE INFOCOM’91 1360–1366. Bat Harbour, FL.
  • Leland, W. E., Taqqu, M., Willinger, W. and Wilson, D. V. (1994). On the self-similar nature of Ethernet traffic (extended version). IEEE/ACM Transactions on Networking 2 1–15.
  • Paxson, V. and Floyd, S. (1995). Wide area traffic: The failure of Poisson modeling. IEEE/ACM Transactions on Networking 3 236–244.
  • Philbrick, S. W. (1985). A practical guide to the single parameter Pareto distribution. In Proceedings of the Casualty Actuarial Society LXXII 44–123. Boca Raton, FL.
  • Prabhu, N. U. (1998). Stochastic Storage Processes: Queues, Insurance Risk, Dams, and Data Communication. Springer, Berlin.
  • Ramírez, P., Lillo, R. E. and Wiper, M. P. (2008). Bayesian analysis of a queueing system with a long-tailed arrival process. Comm. Statist. Simulation Comput. 4 697–712.
  • Ramírez, P., Lillo, R. E., Wilson, S. and Wiper, M. P. (2010). Supplement to “Bayesian inference for double Pareto Lognormal queues.” DOI: 10.1214/10-AOAS336SUPP.
  • Reed, W. J. and Jorgensen, M. (2004). The double Pareto–lognormal distribution—A new parametric model for size distributions. Comm. Statist. Theory Methods 33 1733–1753.
  • Resnick, S. I. (1997). Heavy tail modeling and teletraffic data. Ann. Statist. 25 1805–1848.
  • Robert, C. P. (2001). The Bayesian Choice. Springer, New York.
  • Rolski, T., Schmidli, H., Schmidt, V. and Teugels, J. (1999). Stochastic Processes for Insurance and Finance. Wiley, Chichester.
  • Shortle, J. F., Brill, P. H., Fischer, M. J., Gross, D. and Massi, D. M. B. (2004). An algorithm to compute the waiting time distribution for the M / G / 1 queue. INFORMS J. Comput. 16 52–161.
  • Shortle, J. F., Fischer, M. J. and Brill, P. H. (2007). Waiting-time distribution of M / DN / 1 queues through numerical Laplace inversion. INFORMS J. Comput. 19 112–120.
  • Sigman, K. (1999). A primer on heavy-tailed distributions. Queueing Syst. 33 261–275.
  • Willinger, W., Paxson, V. and Taqqu, M. S. (1998). Self-similarity and heavy tails: Structural modeling of network traffic. In A Practical Guide to Heavy Tails: Statistical Techniques and Applications (R. Adler, R. Feldman and M. S. Taqqu, eds.) 27–54. Birkhäuser, Boston.
  • Wiper, M. P. (1997). Bayesian analysis of Er / M / 1 and Er / M / c queues. J. Statist. Plann. Inference 69 65–79.

Supplemental materials

  • Supplementary material: Matlab Toolbox. The Matlab toolbox performs Bayesian estimation for the double Pareto Lognormal (dPlN) distribution, and for the queueing systems dPlN / G / 1 and M / dPlN / 1.