Abstract
We consider the discrete three dimensional scan statistics. Viewed as the maximum of an 1-dependent stationary r.v.’s sequence, we provide approximations and error bounds for the probability distribution of the three dimensional scan statistics. Importance sampling algorithm is used to obtain sharp bounds for the simulation error. Simulation results and comparisons with other approximations are presented for the binomial and Poisson models.
Similar content being viewed by others
References
Amarioarei A (2012) Approximation for the distribution of extremes of one dependent stationary sequences of random variables. arXiv:1211.5456v1 (submitted)
Boutsikas MV, Koutras M (2000) Reliability approximations for Markov chain imbeddable systems. Methodol Comput Appl Probab 2:393–412
Darling R, Waterman M (1986) Extreme value distribution for the largest cube in a random lattice. SIAM J Appl Math 46:118–132
Glaz J, Naus J, Wallenstein S (2001) Scan statistic. Springer, New York
Glaz J, Pozdnyakov V, Wallenstein S (2009) Scan statistic: methods and Applications. Birkhauser, Cambridge, MA
Glaz J, Guerriero M, Sen R (2010) Approximations for three dimensional scan statistic. Methodol Comput Appl Probab 12:731–747
Haiman G (1999) First passage time for some stationary sequence. Stoch. Process. Appl. 80:231–248
Haiman G, Preda C (2006) Estimation for the distribution of two-dimensional scan statistics. Methodol Comput Appl Probab 8:373–381
Naiman D, Priebe C (2001) Computing scan statistic p values using importance sampling, with applications to genetics and medical image analysis. J Comput Graph Statist 10:296–328
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Amărioarei, A., Preda, C. Approximation for the Distribution of Three-dimensional Discrete Scan Statistic. Methodol Comput Appl Probab 17, 565–578 (2015). https://doi.org/10.1007/s11009-013-9382-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11009-013-9382-3