Jun 24 – 25, 2019
Prague, Czech Republic
Europe/Prague timezone

Homogeneity tests of weighted samples in ROOT

Jun 24, 2019, 10:50 AM
20m
Lecture room 103 (Prague, Czech Republic)

Lecture room 103

Prague, Czech Republic

Czech Technical University in Prague Břehová 7, 115 19 Prague, Czech Republic

Speaker

Jakub Trusina (Czech Technical University (CZ))

Description

An important part of data analysis is to verify whether measured data have the same distribution as a simulated MC sample. One of several methods of verification is homogeneity testing. MC samples are usually weighted and therefore homogeneity tests must be generalized. In ROOT, some homogeneity tests of weighted samples are implemented; however, none of them performs well. Moreover, they are limited to be applicable only to binned data samples. Therefore, we implemented several tests in ROOT: Kolmogorov-Smirnov, Cramér-von Mises, and Anderson-Darling which use complete samples' information. Asymptotic properties of these modified tests are compared in a simulation.

Primary author

Jakub Trusina (Czech Technical University (CZ))

Co-author

Jiri Franc (Czech Technical University (CZ))

Presentation materials