Two‐Sample McNemar Tests for Complex Survey Data

Jenny Thompson and Robin Fisher

Abstract

Feuer and Kessler (1989) generalized the McNemar test (1947) to a two sample situation where the hypothesis of interest is that the marginal changes in each of two independent sample's tables are equal. We show two refinements of this test for complex survey data, which require different estimates of variance. In particular, we present these tests along with applications from the Current Population Survey's Parallel Survey split panel data and from the Current Population Survey's CATI Phase-in data.