Adjustment to Lancaster's Mid-P

Eugene Seneta (), Geoffrey Berry () and Petra Macaskill ()
Additional contact information
Eugene Seneta: University of Sydney
Geoffrey Berry: University of Sydney
Petra Macaskill: University of Sydney

Methodology and Computing in Applied Probability, 1999, vol. 1, issue 2, 229-240

Abstract: Abstract Lancaster's mid-P is increasingly accepted as an adjustment for the P-value when an integer-valued test statistic W is used (as in Fisher's Exact Test), and is recommended for quoting as a measure of significance with the actual P-value. On the basis of distributional properties of the mid-P which resemble those of a P-value of a continuous test statistic, we propose a further adjustment. This gives a significance value h(w) when W=w is observed, such that and Eh(W)=1/2 and Varh(W)=1/12. A computational algorithm to produce h(w) is suggested. Symmetry of the distribution of W is shown to provide substantial simplification. The numerical procedures are illustrated on 3 examples (2 from real life) to which Fisher's Exact Test is applied. The results are compared with an unconditional test in a concluding section.

Keywords: P-value; integer-valued statistic; Fisher's Exact Test; symmetry; tangent transform (search for similar items in EconPapers)
Date: 1999
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1023/A:1010013405122 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

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:spr:metcap:v:1:y:1999:i:2:d:10.1023_a:1010013405122

Ordering information: This journal article can be ordered from
https://www.springer.com/journal/11009

DOI: 10.1023/A:1010013405122

Access Statistics for this article

Methodology and Computing in Applied Probability is currently edited by Joseph Glaz

More articles in Methodology and Computing in Applied Probability from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().