Extreme Value Results for Scan Statistics

• Michael V. Boutsikas
• Markos V. Koutras
• Fotios S. Milienos
Chapter
Part of the Statistics for Industry and Technology book series (SIT)

Abstract

In the first part of this chapter we focus on the classical scan and multiple scan statistic, defined on a sequence of independent and identically distributed (i.i.d.) binary trials and review a number of bounds and approximations for their distributions which have been developed by the aid of distance measures. Moreover, we discuss briefly a number of asymptotic results that have been established by setting up appropriate conditions guaranteeing the convergence (to zero) of the distance measures’ upper bounds. In the second part, we study a multiple scan statistic enumerating variable by considering a general threshold-based framework, defined on i.i.d. continuous random variables. More specifically, we first prove a compound Poisson approximation for the total number of fixed length overlapping moving windows containing a prespecified number of threshold exceedances. The classical scan and multiple scan statistic may be treated as a special case of this general model. Next we exploit the previous result to gain some new extreme value results for the scan enumerating statistic under the assumption that the continuous random variables belong to the maximum domain of attraction of one of the three extreme value distributions (Fréchet, reversed Weibull, Gumbel). Finally, we elucidate how the general results can be applied in a number of classical continuous distributions (Pareto, uniform, exponential and normal).

Keywords and phrases:

Scan multiple scan statistic  Poisson and compound Poisson approximation Erdős–Rényi statistic extreme value theory maximum domain of attraction moving sums and exceedances

References

1. 1.
Arnold, B.C. (1985). Pareto distributions, In Encyclopedia of Statistical Sciences, S. Kotz, N.L. Johnson and C.B. Read (editors), 568–574, John Wiley & Sons, New York.Google Scholar
2. 2.
Arnold, B.C. and Balakrishnan, N. (1989). Relations, Bounds, and Approximations for Order Statistics, Springer, New York.
3. 3.
Arratia, R.L., Goldstein, L. and Gordon, L. (1990). Poisson approximation and the Chen-Stein method, Statistical Science, 5, 403–423.
4. 4.
Arratia, R.L., Gordon, L. and Waterman, M. (1990). The Erdős-Rényi Law in distribution, for coin tossing and sequence matching, Annals of Statistics, 18, 539–570.
5. 5.
Balakrishnan, N. and Koutras, M.V. (2002). Runs, Scans and Applications, John Wiley & Sons, New York.Google Scholar
6. 6.
Barbour, A.D., Holst, L. and Janson, S. (1992). Poisson Approximation, Clarendon Press, Oxford.
7. 7.
Boutsikas, M.V. and Koutras, M.V. (2001). Compound Poisson approximation for sums of dependent random variables, In Ch.A. Charalambides, M.V. Koutras, N. Balakrishnan (eds), Probability and Statistical Models with Applications, 63–86, Chapman & Hall, Boca Raton, FL.Google Scholar
8. 8.
Boutsikas, M.V. and Koutras, M.V. (2002). Modeling claim exceedances over thresholds, Insurance: Mathematics and Economics, 30, 67–83.
9. 9.
Boutsikas, M.V. and Koutras, M.V. (2006). On the asymptotic distribution of the discrete scan statistic, Journal of Applied Probability, 43, 1137–1154.
10. 10.
Bowers, N.L., Gerber, H.U., Hickman, J., Jones, D.A. and Nesbitt, C.J. (1997). Actuarial Mathematics, 2nd edition, The Society of Actuaries, Illinois.Google Scholar
11. 11.
Chen, J. and Glaz, J. (1999). Approximations for the distribution and the moments of discrete scan statistics, In Scan Statistics and Applications, J. Glaz and N. Balakrishnan, (eds), Birkh\ddot{{ a}}user, Boston, MA.Google Scholar
12. 12.
Coles, S. (2001). An Introduction to Statistical Modeling of Extreme Values, Springer-Verlag, London.
13. 13.
David, H.A. and Nagaraja, H.N. (2003). Order Statistics, (3rd edition), John Wiley & Sons, New York.
14. 14.
Deheuvels, P. and Devroye, L. (1987). Limit laws of Erd\ddot{{ o}}s-Rényi-Shepp type, The Annals of Probability, 15, 1363–1386.
15. 15.
Dembo, A. and Karlin, S. (1992). Poisson approximations for r-scan processes, Annals of Applied Probability, 2, 329–357.
16. 16.
Dudkiewicz, J. (1998). Compound Poisson approximation for extremes for moving minima in arrays of independent random variables, Applicationes Mathematicae, 25, 19–28.
17. 17.
Embrechts, P., Kl\ddot{{ u}}ppelberg, C. and Mikosch, T. (1997). Modeling Extremal Events for Insurance and Finance, Springer-Verlag, Berlin.Google Scholar
18. 18.
Erdős, P. and Rényi, A. (1970). On a new law of large numbers, Journal d’Analyse Mathematique, 23, 103–111.Google Scholar
19. 19.
Fu, J.C. (2001). Distribution of the scan statistic for a sequence of bistate trials, Journal of Applied Probability, 38, 908–916.
20. 20.
Fu, J.C. and Lou, W.Y.W. (2003). Distribution Theory of Runs and Patterns and Its Applications, Word Scientific Publishing, Singapore.
21. 21.
Glaz, J. and Balakrishnan, N. (eds.) (1999). Scan Statistics and Applications, Birkh\ddot{{ a}}user, Boston, MA.Google Scholar
22. 22.
Glaz, J. and Naus, J. (1991). Tight bounds and approximations for scan statistic probabilities for discrete data, The Annals of Applied Probability, 1, 306–318.
23. 23.
Glaz, J., Naus, J. and Wallenstein, S. (2001). Scan Statistics, Springer-Verlag, New York.
24. 24.
Goldstein, L. and Waterman, M. (1992). Poisson, compound Poisson and process approximations for testing statistical significance in sequence comparisons, Bulletin of Mathematical Biology, 54, 785–812.
25. 25.
Johnson, N.L., Kotz, S. and Balakrishnan, N. (1994). Continuous Univariate Distributions, Vol. 1, John Wiley & Sons, New York.
26. 26.
Kotz, S. and Nadarajah, S. (2000). Extreme Value Distributions: Theory and Applications, Imperial College Press, London.
27. 27.
Koutras, M.V. and Alexandrou, V.A. (1995). Runs, scans and run model distributions: a unified Markov chain approach, Annals of the Institute of Statistical Mathematics, 47, 743–766.
28. 28.
Reiss, R.D. and Thomas, M. (1997). Statistical Analysis of Extreme Values, Birkh\ddot{{ a}}user, Basel.Google Scholar