Volatility of selected separators/classifiers wrt. data sets from field of particle physics

0368174 - ÚI 2012 CZ eng V - Výzkumná zpráva
Jiřina, Marcel - Hakl, František
Volatility of selected separators/classifiers wrt. data sets from field of particle physics.
Prague: ICS AS CR, 2011. 10 s. Technical Report, V-1126.
Grant CEP: GA MŠMT(CZ) 1M0567
Výzkumný záměr: CEZ:AV0Z10300504
Klíčová slova: multivariate data * volatility * classification * signal-background separation * physics event data * particle physics
Kód oboru RIV: BB - Aplikovaná statistika, operační výzkum

We study the volatility, i.e. influence of random changes in data sets to overall separation/classification behavior of separators/classifiers. This is motivated by the fact, that simulated data and true data from ATLAS experiment may differ, and a question arises what if separators or cuts are optimized for simulated data, and then used for true data from the experiment. This behavior was studied using simulated data modified by artificial distortions of known size. We found that even slight change in data sets causes a little worse result than supposed but, surprisingly, even relatively large distortions give then nearly the same results. Only truly great variations cause degradation of separation quality of separator/classifier as well as of the cuts method.
Trvalý link: http://hdl.handle.net/11104/0202590