A parameterisation-invariant modification of the score test

P. E. Jupp*

*Corresponding author for this work

Research output: Contribution to journalSpecial issuepeer-review

2 Downloads (Pure)

Abstract

The null distribution of the score test statistic is asymptotically chi-squared for large samples. The error in this approximation is improved greatly by a cubic modification. The coefficients of this cubic that are given in the literature depend on the parameterisation. This paper provides parameterisation-invariant versions of the coefficients, expresses them in terms of appropriate tensors, and provides geometric interpretations.
Original languageEnglish
Pages (from-to)429-439
Number of pages11
JournalInformation Geometry
Volume7
Early online date7 Mar 2023
DOIs
Publication statusPublished - 1 Jan 2024

Keywords

  • Bartlett correction
  • Generalised Bartlett correction
  • Interest parameter
  • Invariant Taylor expansion
  • Large-sample asymptotics
  • Likelihood yoke
  • Tensor

Fingerprint

Dive into the research topics of 'A parameterisation-invariant modification of the score test'. Together they form a unique fingerprint.

Cite this