贝叶斯推断中包含蒙特卡洛统计不确定性的分箱似然
Binned Likelihood including Monte Carlo Statistical Uncertainty in Bayesian Inference
AI总结:
针对有限蒙特卡洛样本统计不确定性难以纳入贝叶斯推断的问题,本文推导了相应的分箱似然,并以更直观的方式得到与已有频率派结果相似的结论。
摘要:
高能物理(HEP)实验中的数据分析通常使用来自数据和有限蒙特卡洛样本的分箱似然。一些文献已在频率派推断中引入蒙特卡洛样本的统计不确定性,但这些方法不适用于贝叶斯推断。本技术说明介绍了贝叶斯推断中带有蒙特卡洛统计不确定性的分箱似然,并包含其推导过程。结果表明,所得结果与文献[1]中的结果相似,但本技术说明为该内容提供了一种替代且更直观的推导。
英文摘要:
Data analysis in HEP experiments often uses binned likelihood from data and finite Monte Carlo sample. Statistical uncertainty of Monte Carlo sample has been introduced in Frequentist Inference in some literatures, but they are not suitable for Bayesian Inference. This technical note introduces the binned likelihood with Monte Carlo statistical uncertainty in Bayesian Inference and includes the derivation of it. It turns out that the results are similar to the results in [1]. But this tech-note gives an alternate and more intuitive derivation of the content
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。