Discrete, Continuous and Conditional Variable Window Scan Statistics
- 2013-01-28 (Mon.), 10:30 AM
- Recreation Hall, 2F, Institute of Statistical Science
- Professor Tung-Lung Wu
- Department of Statistics, University of Connecticut, USA
Abstract
Discrete, Continuous and Conditional Variable Window Scan Statistics Professor Tung-Lung Wu Department of Statistics, University of Connecticut, USA ? The literature on the scan statistics is substantial and growing rapidly due to the widespread applications in many areas, such as genetics and quality control. The distributions of discrete, continuous and conditional variable window scan statistics are studied.? The finite Markov chain imbedding technique has been applied to obtain the distributions of fixed window scan statistics defined from a sequence of Bernoulli trials. The technique is extended to obtain the exact and approximate distributions of discrete and continuous variable window scan statistics, respectively. The exact powers for multiple pulse and Markov dependent alternatives are also obtained.? An application in blood component quality monitoring is provided. Numerical results are also given to illustrate our theoretical results.