Abstract
When investigators have N pairs of binary data, a common test for an increased rate of response is McNemar's test. However, McNemar's is an approximate, conditional test. An exact, unconditional test exists, but requires restrictive assumptions. Critical values and power tables are presented for an exact, unconditional test free of these assumptions. Copyright © 2002 JMASM, Inc.
DOI
10.22237/jmasm/1020255060
Year