A New Test for 2 × 2 Tables

@article{Barnard1945ANT,
  title={A New Test for 2 × 2 Tables},
  author={George A. Barnard},
  journal={Nature},
  year={1945},
  volume={156},
  pages={177}
}
  • G. Barnard
  • Published 1 August 1945
  • Mathematics
  • Nature
IF an experiment yields results in the form of a 2 × 2 table: 
A New Test for 2 × 2 Tables
UNDER this heading, G. A. Barnard1 puts forward a test which, in language adopted from Neyman and Pearson, “is more powerful than Fisher's”. This means in practice that the test advocated passes as
Fisher's Exact Probability Test for Cross-Classification Tables
TLDR
Algorithms and associated FORTRAN subroutines for the Fisher exact probability test are presented and the use of recursion and an arbitrary initial value ensures computational efficiency.
SOME ISSUES ARISING FROM THE ANALYSIS OF 2×2 CONTINGENCY TABLES
Summary We review the 40 year old controversy over the correct analysis of 2×2 tables. It is argued that conditioning on all marginal totals is appropriate by examining the likelihood based on
The analysis of 2 × 1 and 2 × 2 contingency tables: an historical review
TLDR
The historical development of analytic techniques for frequency data presented as 2 x 1 or 2 x 2 contingency tables is described and a single statistic approximating the chi-square distribution is used to test the hypothesis of an association between the two relevant variables.
Permutation and Rank Tests
In the early 1930s R. A. Fisher discovered a very general exact method of testing hypotheses based on permuting the data in ways that do not change its distribution under the null hypothesis. This
Power calculations in SAS® of exact small-sample tests for 2Ũ2 -tables
Exact tests for 2×2 - tables are compared in small sample situations: FISHER, LIEBERMEISTER, BARNARD. The respective power and the type I error are calculated in a SAS®-environment.
Exact Power of Conditional and Unconditional Tests: Going beyond the 2 × 2 Contingency Table
Abstract The controversial question of whether one should condition on both margins of a contingency table for exact inference is examined from a fresh, computational perspective. The conditional
On alleged gains in power from lower P-values.
TLDR
One-sided tests are examined in detail but two-sided test problems are also considered and the need for flexibility in use of P-values is stressed.
Raised conditional level of significance for the 2 × 2‐table when testing the equality of two probabilities
In this paper it is to be shown that Fisher's non‐randomizing exact test for 2 × 2‐tables, which is a conditional test, can by simple means be changed into an unconditional test using raised levels
...
...

References

SHOWING 1-4 OF 4 REFERENCES
A New Test for 2 × 2 Tables
UNDER this heading, G. A. Barnard1 puts forward a test which, in language adopted from Neyman and Pearson, “is more powerful than Fisher's”. This means in practice that the test advocated passes as
THE INTERPRETATION OF EXPERIMENTAL FOUR-FOLD TABLES
TLDR
In advocating the particular method he chooses for the interpretation of data of this important class he has, I believe, overlooked a difficulty which the approach based on, and giving the exact solution for, the classical view-point of x2 and the four-fold table was expressly devised to obviate.