fishertest
Fisher’s exact test.
h = fishertest (x) performs Fisher’s exact test on a
contingency table given in matrix x. This is a test of the
hypothesis that there are no non-random associations between the two 2-level
categorical variables in x. fishertest returns the result of
the tested hypothsis in h. h = 0 indicates that the null
hypothesis (of no association) cannot be rejected at the 5% significance
level. h = 1 indicates that the null hypothesis can be rejected at the
5% level. x must contain only non-negative integers. Use the
crostab function to generate the contingency table from samples of two
categorical variables. Fisher’s exact test is not suitable when all integers
in x are very large. Use can use the Chi-square test in this case.
[h, pval] = fishertest (x) returns the p-value in
pval. That is the probability of observing the given result, or one
more extreme, by chance if the null hypothesis is true. Small values of
pval cast doubt on the validity of the null hypothesis.
[p, pval, stats] = fishertest (…) returns the
structure stats with the following fields:
OddsRatio | – the odds ratio | |
ConfidenceInterval | – the asymptotic confidence
interval for the odds ratio. If any of the four entries in the contingency
table x is zero, the confidence interval will not be computed, and
[-Inf Inf] will be displayed. |
[…] = fishertest (…, name, value, …)
specifies one or more of the following name/value pairs:
| Name | Value | |
|---|---|---|
"alpha" | the significance level. Default is 0.05. | |
"tail" | a string specifying the alternative hypothesis |
"both" | odds ratio not equal to 1, indicating association between two variables (two-tailed test, default) | |
"left" | odds ratio greater than 1 (right-tailed test) | |
"right" | odds ratio is less than 1 (left-tailed test) |
See also: crosstab, chi2test, mcnemar_test, ztest2
Source Code: fishertest
## A Fisher's exact test example
x = [3, 1; 1, 3]
[h, p, stats] = fishertest(x)
x =
3 1
1 3
h = 0
p = 0.4857
stats =
scalar structure containing the fields:
OddsRatio = 9
ConfidenceInterval =
0.3666 220.9270
|