chi2_mcnemar(M)
Computes a McNemar test using data in matrix M and a significance level of 0.05 (5%). Matrix M must be a contingency table.
chi2_mcnemar(M, alpha)
As above but the significance level is alpha.
See also chi2_likelihood chi2_kappa chi2_mantel chi2_risk
Example
A total of 20 teenagers were interviewed about their views on the death penalty; the study found that 12 were in favor of the death penalty and 8 were against it. Afterward, the youths were given lectures and attended seminars on the errors and abuse of the death penalty; a week later they were interviewed again.
The table below shows their opinions before and after:
|
|||
The data shows that all but one youth changed from in favor to against while 3 youths changed from against to in favor.
Entering the basic data in a matrix we obtain:
M = ( 1, 11; 3, 5)
/ 1 11 \
\ 3 5 /
We now use function chi2_totable to transform the matrix into a proper contingency table
M=chi2_totable(M)
/ "" "" "" "" \
| "" 1 11 16 |
| "" 3 5 8 |
\ "" 4 16 20 /
Using the function chi2_mcnemar we obtain (5% significance),
chi2_mcnemar(M)
McNemar test.
Hypothesis test assumes a two-tails test for changes in response. For other tests use the one-tail probability.
Ho : Proportions before and after are the same
Ha : Proportions before and after are not the same
Significance level : 0.05 (5.0%)
Results:
Do not reject the null hypothesis. (1.0)
Two-tails probability: 0.05737304687500008
For other test use:
One-tail probability: 0.02868652343750004