PyHEP 2020 (virtual) Workshop

Model building and statistical inference with zfit and hepstats

Not scheduled

45m

Tutorial Fitting & statistics

Speakers

Jonas Eschle (Universitaet Zuerich (CH)) Matthieu Marinangeli (EPFL - Ecole Polytechnique Federale Lausanne (CH))

Description

zfit is a model fitting library based on top of TensorFlow and built for customization. It can build models, load data, create and optimize losses. hepstats is a package for statistical inference and is build on top of the zfit interface, and can therefore use models and losses built in zfit directly.

In this tutorial, we propose to split the tutorial into two parts (switching speaker in-between): we first give an introduction (~30 mins) to zfit ranging from simple mass fits to more complicated examples including custom built PDFs and simultaneous fits. The second part (~15 mins) consists of an introduction to hepstats using the models and losses built before in zfit for statistical inference including limit setting and confidence intervals.

The tutorial is targeted towards beginners regarding the experience with zfit or hepstats.