Abstract
Wallenstein et al. (1994) discussed the power via combinatorial calculations for scan statistics against a pulse alternative given certain proper conditions. Our work extends their results and provides an alternative way to obtain the distribution of a scan statistic under various alternative conditions. An efficient and intuitive expression for the distribution as well as power of the scan statistic is introduced via finite Markov chain imbedding (FMCI). The numerical results of the power for a discrete scan statistic against various conditions are presented.
Similar content being viewed by others
References
Fu JC (2001) Distribution of the scan statistic for a sequence of bistate trials. J Appl Probab 38:908–916
Fu JC, Johnson BC (2009) Approximate probabilities for runs and patterns in i.i.d. and Markov-dependent multistage trials. Adv Appl Probab 41:292–308
Fu JC, Wu TL, Lou WYW (2012) Continuous, discrete and conditional scan statistics. J Appl Probab 49:199–209
Hoh J, Ott J (2000) Scan Statistics to Scan Markers for Susceptibility Genes. Proc Natl Acad Sci U S A 97:9615–9617
Naus J (1974) Probabilities for a generalized birthday problem. J Am Stat Assoc 69:810–815
Wallenstein S, Naus J, Glaz J (1994) Power of the scan statistic in detecting a changed segment in a Bernoulli sequence. Biometrika 81:595–601
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lee, WC. Power of Discrete Scan Statistics: a Finite Markov Chain Imbedding Approach. Methodol Comput Appl Probab 17, 833–841 (2015). https://doi.org/10.1007/s11009-014-9434-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11009-014-9434-3