The perceived framework of a classical statistic: Is the non-invariance of a Wald statistic much ado about null thing?

Noxy Dastoor

No 2009-25, Working Papers from University of Alberta, Department of Economics

Abstract: The distinction between a nominal framework for the three classical statistics and a perceived framework for each classical statistic provides more ways to interpret these statistics, and intuitively explains as well as more easily shows some well-known results. In particular, each classical statistic can be viewed in terms of a length in each of four spaces and, since the classical procedures per se are equivalent in a perceived framework, two statistics are identical if their perceived frameworks are identical. This helps to integrate the normally separately treated issues of a reformulation of a null hypothesis and of locally equivalent alternatives. For example, a Wald statistic is not invariant if a reformulation changes its perceived framework, and an appropriate score statistic is invariant as its perceived framework is unaffected by considering a locally equivalent alternative. [During the thirty-four months this paper was under consideration at The Econometrics Journal, the Editor-in-charge (Professor Stephane Gregoir) did not reply to three (of the author's four) requests about the status of the submission, and provided neither a referee's report nor a first decision. Also, when asked to intervene by the author, the new Managing Editor (Professor Richard J Smith) offered the author the possibility of submitting the paper (as a new submission) to the new editorial regime, at which point, the author withdrew the paper.]

Keywords: classical statistic; likelihood ratio statistic; nominal framework; perceived framework; score statistic; Wald statistic (search for similar items in EconPapers)
JEL-codes: C12 (search for similar items in EconPapers)
Pages: 43 pages
Date: 2009-08-01
New Economics Papers: this item is included in nep-ecm and nep-hpe
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://sites.ualberta.ca/~econwps/2009/wp2009-25.pdf Full text (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ris:albaec:2009_025

Access Statistics for this paper

More papers in Working Papers from University of Alberta, Department of Economics Contact information at EDIRC.
Bibliographic data for series maintained by Joseph Marchand ().