From agenda setting to refusal setting

Past research suggests that there is a relationship between survey response and topic salience, namely that individuals responding to a survey are likely to find the survey topic more salient than nonrespondents do. For election surveys, nonresponse resulting from a lack of salience can influence findings because respondents may be more interested in politics than nonrespondents. The agenda-setting model suggests that media coverage should heighten salience. Thus, as media coverage of political campaigns increases over the course of an election, refusals to a political survey should decline. Using data from the National Annenberg Election Survey (NAES), which was conducted nearly continuously in 2004, this study investigates the issue of nonresponse in a random digit dial telephone survey across the election cycle by examining daily changes in the refusal rates using time-series analysis. Content analyses of the frequencies of presidential campaign stories mentioned in the New York Times and three network news broadcasts were matched against a time series from the NAES to demonstrate that increases in media coverage of the election were negatively related to the survey refusal rate.