pyhf: pure-Python implementation of HistFactory statistical models
pyhf: pure-Python implementation of HistFactory statistical models
复制标题
DOI：
10.21105/joss.02823
复制
发表时间：
2021-02
期刊：
影响因子：
--
通讯作者：
L. Heinrich;M. Feickert;G. Stark;K. Cranmer
中科院分区：
文献类型：
--
作者：
L. Heinrich;M. Feickert;G. Stark;K. Cranmer
高能物理（HEP）数据的统计分析依赖于量化观测到的碰撞事件与理论预测的兼容性。它们之间的关系通常形式化为一个统计模型f（x j），描述给定模型参数的数据x的概率。给定观测数据，似然L（k）然后用作推断参数k的基础。对于基于分箱数据（直方图）的测量，统计模型的HistFactory家族（Cranmer等人，2012）已被广泛用于标准模型测量（ATLAS协作，2013）以及搜索新物理（ATLAS协作，2018）。pyhf是HistFactory模型规范的纯Python实现，并且实现了用于描述基于HistFactory的可能性的声明性纯文本格式，其目标是在分析数据存储库（诸如HEPData）中进行重新解释和长期保存（Maguire等人，2017年）。pyhf的源代码已在Zenodo上存档，并链接了DOI：（Heinrich，Lukas和Feickert，Matthew和Stark，Giordon，2020）。在撰写本文时，pyhf的最新版本是
Statistical analysis of High Energy Physics (HEP) data relies on quantifying the compatibility of observed collision events with theoretical predictions. The relationship between them is often formalised in a statistical model f ( x j ϕ ) describing the probability of data x given model parameters ϕ . Given observed data, the likelihood L ( ϕ ) then serves as the basis for inference on the parameters ϕ . For measurements based on binned data (histograms), the HistFactory family of statistical models (Cranmer et al., 2012) has been widely used in both Standard Model measurements (ATLAS Collaboration, 2013) as well as searches for new physics (ATLAS Collaboration, 2018). pyhf is a pure-Python implementation of the HistFactory model specification and implements a declarative, plain-text format for describing HistFactory - based likelihoods that is targeted for reinterpretation and long-term preservation in analysis data repositories such as HEPData (Maguire et al., 2017). The source code for pyhf has been archived on Zenodo with the linked DOI: (Heinrich, Lukas and Feickert, Matthew and Stark, Giordon, 2020). At the time of writing this paper, the most recent release of pyhf is