USING DUAL FRAME DESIGNS TO REDUCE NONRESPONSE IN TELEPHONE SURVEYS

This article reports on the results of a series of experimentsdesigned to improve response rates for telephone surveys. Inthree surveys telephone households were selected using bothstandard random digit dialing (RDD) techniques and lists oftelephone numbers purchased from a commercial firm. In the RDDportions of the samples "cold contact" interviewing methodswere used; in the list frame portions advance letters were mailed,and the listed household name was used in the introduction.Experiments were designed to test the effects on response ratesof the advance letters and use of the listed household nameas a means of establishing rapport. The advance letters increasedresponse rates, but no difference could be attributed to theuse of names. The mixture of RDD and list sampling techniquesis also used to evaluate the effects of relative response rateson substantive findings. The cost consequences of these dualframe designs are assessed along a number of dimensions, andthe cost and error components of these designs are discussed.     

The Consequences of Validated and Self-Reported Voting Measures

This paper reports on the results of validation of the self-reportedregistration status and voting behavior of respondents in the1976 and 1978 American National Election Studies. The resultsindicate about one in seven of the respondents misreported theirregistration status or voting behavior. Comparative analysesare conducted using simple regression models to see if differencesin their explanatory power arise using validated and self-reporteddependent variables. The results show that there are no majorchanges in the fundamental nature of basic relationships thathave been observed since the first surveys were conducted. Analysisof the effects of overreported participation on estimates ofthe partisan division of the vote in three sets of subnationalcontests reveals a likely "bandwagan" effect. . Portions of the data utilized in this article were made availableby the Inter-university Consortium for Political and SocialResearch. The data for the 1976 and 1978 American National ElectionStudies were originally collected by the Center for PoliticalStudies of the Institute for Social Research. The Universityof Michigan, under a grant from the National Science Foundation.Neither the original collectors of the data nor the Consortiumbear any responsibility for the analyses or interpretationspresented here. The comments of an anonymous reviewer, whichresulted in a fruitful extension of the analysis, are gratefullyacknowledged.     

THE IMPORTANCE OF PERSISTENCE IN RESPONDENT SELECTION FOR PREELECTION SURVEYS

Different techniques for respondent selection can affect dataquality. These differences can result in variations in the distributionof partisans in preelection surveys, which in turn can havean effect on the distribution of candidate preference. Persistencein trying to interview designated respondents in telephone householdsincreased the number of Republicans in a 1984 sample, and thereforeReagan's margin over Mondale. Such differences in interviewingtechniques might account for some of the variations in nationalpreelection estimates of the outcome of the presidential election,and they suggest that caution be used in comparing marginalsfor party identification from different surveys employing differentrespondent selection techniques.     

LITTLE WHITE LIES AND SOCIAL SCIENCE MODELS CORRELATED RESPONSE ERRORS IN A PANEL STUDY OF VOTING

One interpretation for the common survey finding that the backgroundcharacteristics of vote overreporters resemble those of actualvoters is that misreporters usually vote. This hypothesis—thatmisreporters regularly voted in earlier elections—is testedwith data from the 1972–74–76 Michigan ElectionPanel. It receives no support: the 1972 and 1974 validated turnoutof the 1976 misreporters was very low. Moreover, misreportingwas a fairly stable respondent characteristic: misreportingabout an election in one interview was correlated with misreportingabout the remaining elections in each of the other two interviews.A comparison of regressions predicting turnout using the validatedreports versus the self-reports shows that the respondent errorscan distort conclusions about the correlates of voting. Forexample, controlling for three other variables, education wasrelated to self-reported voting but not to validated voting.Here, as well as in surveys of other socially desirable or undesirableissues, respondent self-reports may bias survey data in favorof commonsense models of the world.     

Response Validity in Surveysof Voting Behavior

This paper presents the results of a project which validatedthe reported registration and voting behavior of respondentsin a national election study. The accuracy of reported votingbehavior in the 1976 general election is assessed in terms ofthe demographic characteristics of the respondents to the Centerfor Political Studies National Election Study as well as theextent of their participation in a survey panel begun in 1972.Increased levels of registration and turnout are observed inassociation with the number of interviews in which respondentsparticipated, and three alternative social psychological modelsof the effects of preelection interviews are evaluated. Althoughthe interview apparently served as a stimulus to voting, neithera model associated with self-concept theory nor alienation theoryappears to explain the phenomenon adequately. The intervieweffect is significant and appears to be cumulative, indicatingthat researchers usingthe survey method with panel designs shouldbe sitive to the effects of their method on the behavior whichthey are tryingto measure.