29 July 2019 to 2 August 2019
Northeastern University
US/Eastern timezone

Combined Neyman-Pearson Chi-square: an improved approximation to the Poisson-likelihood chi-square

30 Jul 2019, 14:20
20m
Shillman 425 (Northeastern University)

Shillman 425

Northeastern University

Oral Presentation Computing, Analysis Tools, & Data Handling Computing, Analysis Tools, & Data Handling

Speaker

Dr Xiangpan Ji (Brookhaven National Lab)

Description

We present a new method to approximate the widely-used Poisson-likelihood chi-square using a linear combination of Neyman's and Pearson's chi-squares, namely ``combined Neyman-Pearson chi-square'' (CNP). Through analytical derivation and toy model simulations, we show that CNP leads to a significantly smaller bias on the best-fit normalization parameter compared to that using either Neyman's or Pearson's chi-square. When the computational cost of using the Poisson-likelihood chi-square is high, CNP provides a good alternative given its natural connection to the covariance matrix formalism.

Primary author

Dr Xiangpan Ji (Brookhaven National Lab)

Co-authors

Chao Zhang (Brookhaven National Laboratory) Hanyu Wei Wenqiang Gu (Brookhaven National Laboratory (US)) Xin Qian (Brookhaven National Laboratory)

Presentation Materials