From Wikipedia, the free encyclopedia  View original article
This article may be too technical for most readers to understand. (November 2012) 
In statistics, McNemar's test is a statistical test used on paired nominal data. It is applied to 2 × 2 contingency tables with a dichotomous trait, with matched pairs of subjects, to determine whether the row and column marginal frequencies are equal (that is, whether there is "marginal homogeneity"). It is named after Quinn McNemar, who introduced it in 1947.^{[1]} An application of the test in genetics is the transmission disequilibrium test for detecting linkage disequilibrium.^{[2]}
The test is applied to a 2 × 2 contingency table, which tabulates the outcomes of two tests on a sample of n subjects, as follows.
Test 2 positive  Test 2 negative  Row total  
Test 1 positive  a  b  a + b 
Test 1 negative  c  d  c + d 
Column total  a + c  b + d  n 
The null hypothesis of marginal homogeneity states that the two marginal probabilities for each outcome are the same, i.e. p_{a} + p_{b} = p_{a} + p_{c} and p_{c} + p_{d} = p_{b} + p_{d}.
Thus the null and alternative hypotheses are^{[1]}
Here p_{a}, etc., denote the theoretical probability of occurrences in cells with the corresponding label.
The McNemar test statistic is:
The statistic with Yates's correction for continuity^{[3]} is given by:^{[4]}
An alternative correction of 1 instead of 0.5 is attributed to Edwards ^{[5]} by Fleiss,^{[6]} resulting in a similar equation:
Under the null hypothesis, with a sufficiently large number of discordants (cells b and c), has a chisquared distribution with 1 degree of freedom. If either b or c is small (b + c < 25) then is not wellapproximated by the chisquared distribution.^{[citation needed]} The binomial distribution can be used to obtain the exact distribution for an equivalent to the uncorrected form of McNemar's test statistic.^{[7]} In this formulation, b is compared to a binomial distribution with size parameter equal to b + c and "probability of success" = ½, which is essentially the same as the binomial sign test. For b + c < 25, the binomial calculation should be performed, and indeed, most software packages simply perform the binomial calculation in all cases, since the result then is an exact test in all cases. When comparing the resulting statistic to the right tail of the chisquared distribution, the pvalue that is found is twosided, whereas to achieve a twosided pvalue in the case of the exact binomial test, the pvalue of the extreme tail should be multiplied by 2.
If the result is significant, this provides sufficient evidence to reject the null hypothesis, in favour of the alternative hypothesis that p_{b} ≠ p_{c}, which would mean that the marginal proportions are significantly different from each other.
In the following example, a researcher attempts to determine if a drug has an effect on a particular disease. Counts of individuals are given in the table, with the diagnosis (disease: present or absent) before treatment given in the rows, and the diagnosis after treatment in the columns. The test requires the same subjects to be included in the beforeandafter measurements (matched pairs).
After: present  After: absent  Row total  
Before: present  101  121  222 
Before: absent  59  33  92 
Column total  160  154  314 
In this example, the null hypothesis of "marginal homogeneity" would mean there was no effect of the treatment. From the above data, the McNemar test statistic with Yates's continuity correction is
has the value 21.01, which is extremely unlikely to form the distribution implied by the null hypothesis. Thus the test provides strong evidence to reject the null hypothesis of no treatment effect.
An interesting observation when interpreting McNemar's test is that the elements of the main diagonal do not contribute to the decision about whether (in the above example) pre or posttreatment condition is more favourable.
An extension of McNemar's test exists in situations where independence does not necessarily hold between the pairs; instead, there are clusters of paired data where the pairs in a cluster may not be independent, but independence holds between different clusters.^{[citation needed]} An example is analyzing the effectiveness of a dental procedure; in this case, a pair corresponds to the treatment of an individual tooth in patients who might have multiple teeth treated; the effectiveness of treatment of two teeth in the same patient is not likely to be independent, but the treatment of two teeth in different patients is more likely to be independent.^{[8]}
John Rice wrote:^{[9]}
85 Hodgkin's patients [...] had a sibling of the same sex who was free of the disease and whose age was within 5 years of the patient's. These investigators presented the following table:
They calculated a chisquared statistic of 1.53, which is not significant.[...] [they] had made an error in their analysis by ignoring the pairings.[...] [their] samples were not independent, because the siblings were paired [...] we set up a table that exhibits the pairings:
It is to the second table that McNemar's test can be applied. Notice that the sum of the numbers in the second table is 85—the number of pairs of siblings—whereas the sum of the numbers in the first table is twice as big, 170—the number of individuals. The second table gives more information than the first. The numbers in the first table can be found by using the numbers in the second table, but not vice versa. The numbers in the first table give only the marginal totals of the numbers in the second table.
