Measuring Public Support for the New Christian Right: The Perils of Point Estimation

In: Public opinion quarterly: journal of the American Association for Public Opinion Research, Volume 52, Issue 3, p. 325-337

Abstract

John H. Simpson has estimated ("Moral Issues and Status Politics" in Liebman, Robert, & Wuthnow, Robert [Eds], The New Christian Right, New York: Aldine, 1983, 187-205) that 30% of US adults support the sociomoral platform of the Moral Majority. Several criticisms of this estimate &/or the way it has subsequently been interpreted are offered, including the treatment of "don't know" responses, the selection of response category cutting points, datedness of data, the effects of question wording, & substance. Analysis of other items from this data set (the 1977 NORC General Social Survey) results in a much different estimate of public support for the Moral Majority platform. More basically, however, results demonstrate that PO on such complex issues cannot be fairly reflected by a single number. In A Reply to "Measuring Public Support for the New Christian Right: The Perils of Point Estimation," John H. Simpson (U of Toronto, Ontario) contends that his original goal was not to produce a point estimate, but to test a multiple indicator measurement model using the maximum likelihood latent structure analysis technique. The good fit of this model to the observed data is described, & it is concluded that Sigelman's & Presser's criticisms either have no bearing on or do not affect the observed frequencies. Major differences between electoral politics & the politics of public policy formation are reiterated. 4 Tables, 27 References. K. Hyatt