Chapter 15
Statistical Issues in Particle Physics
Louis Lyons
15.1 Introduction
In recent years there has been a growing awareness by particle physicists of the
desirability of using good statistical practice. This is because the accelerator and
detector facilities have become so complex and expensive, and involve so much
physicist effort to build, test and run, that it is clearly important to treat the data with
respect, and to extract the maximum information from them. The PHYSTAT series
of Workshops and Conferences[1–12] has been devoted specifically to statistical
issues in particle physics and neighbouring fields, and many interesting articles can
be found in the relevant Proceedings. These meetings have benefited enormously
from the involvement of professional statisticians, who have been able to provide
specific advice as well as pointing us to some techniques which had not yet filtered
down to Particle Physics analyses.
Analyses of experimental data in Particle Physics have, perhaps not surprisingly,
tended to use statistical methods that have been described by other Particle Physicists. There are thus several books written on the subject by Particle Physicists[13].
The Review of Particle Physics properties[14] contains a condensed review of
Statistics.
Another source of useful information is provided by the statistics committees
set up by some of the large collaborations (see, for example, refs. [15–18]). Some
conferences now include plenary talks specifically on relevant statistical issues
(for example, Neutrino 2017[19], NuPhys17 and NuPhys18[20]), and the CERN
L. Lyons ()
Physics, University of Oxford, Oxford, UK
e-mail: louis.lyons@physics.ox.ac.uk
© The Author(s) 2020
C. W. Fabjan, H. Schopper (eds.), Particle Physics Reference Library,
https://doi.org/10.1007/978-3-030-35318-6_15
645
Statistical Issues in Particle Physics
Louis Lyons
15.1 Introduction
In recent years there has been a growing awareness by particle physicists of the
desirability of using good statistical practice. This is because the accelerator and
detector facilities have become so complex and expensive, and involve so much
physicist effort to build, test and run, that it is clearly important to treat the data with
respect, and to extract the maximum information from them. The PHYSTAT series
of Workshops and Conferences[1–12] has been devoted specifically to statistical
issues in particle physics and neighbouring fields, and many interesting articles can
be found in the relevant Proceedings. These meetings have benefited enormously
from the involvement of professional statisticians, who have been able to provide
specific advice as well as pointing us to some techniques which had not yet filtered
down to Particle Physics analyses.
Analyses of experimental data in Particle Physics have, perhaps not surprisingly,
tended to use statistical methods that have been described by other Particle Physicists. There are thus several books written on the subject by Particle Physicists[13].
The Review of Particle Physics properties[14] contains a condensed review of
Statistics.
Another source of useful information is provided by the statistics committees
set up by some of the large collaborations (see, for example, refs. [15–18]). Some
conferences now include plenary talks specifically on relevant statistical issues
(for example, Neutrino 2017[19], NuPhys17 and NuPhys18[20]), and the CERN
L. Lyons ()
Physics, University of Oxford, Oxford, UK
e-mail: louis.lyons@physics.ox.ac.uk
© The Author(s) 2020
C. W. Fabjan, H. Schopper (eds.), Particle Physics Reference Library,
https://doi.org/10.1007/978-3-030-35318-6_15
645