In the study of stochastic processes in mathematics, a disorder problem or quickest detection problem (formulated by Kolmogorov) is the problem of using ongoing observations of a stochastic process to detect as soon as possible when the probabilistic properties of the process have changed. This is a type of change detection problem.
An example case is to detect the change in the drift parameter of a Wiener process.1
Notes
Notes
- Shiryaev (2007) page 208
References
References
- H. Vincent Poor and Olympia Hadjiliadis (2008). Quickest Detection (First ed.). Cambridge: Cambridge University Press. ISBN 978-0-521-62104-5.
- Shiryaev, Albert N. (2007). Optimal Stopping Rules. Springer. ISBN 978-3-540-74010-0.
- Gapeev, P.V. (2005). "The disorder problem for compound Poisson processes with exponential jumps". Ann. Appl. Probab. 15 (1A): 487–499. arXiv:math/0503481. doi:10.1214/105051604000000981.
- Kolmogorov, A. N., Prokhorov, Yu. V. and Shiryaev, A. N. (1990). Methods of detecting spontaneously occurring effects. Proc. Steklov Inst. Math. 1, 1–21.