Two by two

About Fisher exact

Calculates the exact probability of occurrence of a two-by-two contingency table and the sum of probabilities of all more extreme cases.

Requires

The grand total of the table must not exceed 170. Only positive integer values are allowed. The test is designed for small samples.

About McNemar/Yates

Allows the significance of differences between two related samples to be determined where the frequencies of discrete categories are known. The measurements require no more than nominal scaling.

Feature

A Yates correction is carried out if the data are from a two-by-two matrix.

Parameters

Two by two dialog

Source

Data from

Dataset
Data is retrieved from the current Dataset:

The currently highlighted selection is loaded for analysis. If more than two rows or columns are included in the selection then only cells at the four corners are used.
Changes you make to Column popups and Row numbers automatically update the values loaded.

Ad hoc
The column popups and row numbers are disabled and the four data values can be entered directly into the dialog

Test

Fisher Exact
McNewmar Yates

Options

Subtitle

Allows you to specify an optional subtitle which will be included in the statistical output.

Buttons

?

Opens the help system for this dialog.

Dataset…

Sends the output from this analysis to a new OxonStat Dataset. See Dataset output for more details.

Print…

Sends the output from this analysis to a printer.

Cancel

Cancels the analysis and closes the dialog.

Screen…

Displays the output from this analysis in the Results window.

Sample output

Fisher Exact

OxonStat

21:14, 10 Sep 2026

Statistic:	Two by Two
Option:	Fisher Exact
Subtitle:	<none>

	Sex	Dia_BP
ID00001	2.0000	88.0000
ID00002	2.0000	58.0000

	p
Exact probability	0.3499
Sum extremes	0.5260

McNewmar Yates

OxonStat

21:16, 10 Sep 2026

Statistic:	Two by Two
Option:	McNemar/Yates
Subtitle:	<none>

	Sex	Dia_BP
ID00001	2.0000	88.0000
ID00002	2.0000	58.0000

	Chi-square	df	p
Yates correction	50.417	1	<0.0001
Without correction	52.267	1	<0.0001