Programs in Physics & Physical Chemistry
|[Licence| Download | New Version Template] adta_v1_0.tar.gz(364 Kbytes)|
|Manuscript Title: A program for confidence interval calculations for a Poisson process with background including systematic uncertainties: POLE 1.0.|
|Authors: J. Conrad|
|Program title: pole version 1.0|
|Catalogue identifier: ADTA_v1_0|
Distribution format: tar.gz
|Journal reference: Comput. Phys. Commun. 158(2004)117|
|Programming language: Fortran 77.|
|Computer: DELL PC, 1 GB 2 Ghz Pentium IV.|
|Operating system: RH linux 7.2 Kernal 2.4.7-10.|
|RAM: 1M words|
|Keywords: Confidence interval calculation, Systematic uncertainties, General purpose, Statistical methods.|
Nature of problem:
The problem is to calculate a frequentist confidence interval on the parameter of a Poisson process with known background in the presence of systematic uncertainties in experimental parameters such as signal efficiency or background prediction.
A PDF for the confidence interval construction is constructed by folding a Poisson density function with a parametrization describing the posterior PDF of the systematic uncertainties. The construction is then performed with this new PDF according to different ordering schemes. The convolution is performed using a Monte Carlo integration method, providing greatest possible flexibility with respect to the parametrization.
POLE uses routines from the CERNLIB library which have to be linked in during compilation. It should be noted that the number of steps in signal space (maximal s required divided by the step-width) should not exceed 1000, since the corresponding arrays are predimensioned.
For the calculation of a single confidence interval with 1000 steps in signal hypothesis space the wall clock time on a DELL PC 1GB 2.0 Ghz Pentium IV with 4 GB swap is ca. 500 seconds. The wall clock time scales roughly linearly with the number of steps in signal space.
|Disclaimer | ScienceDirect | CPC Journal | CPC | QUB|