PRE-ELECTION POLITICAL POLLING AND THE NON-RESPONSE BIAS ISSUE     

Shaiko  Ronald G.; Dwyre  Diana; O'Gorman  Mark; Stonecash  Jeffrey M.; Vike  James 《Int. Journal of Public Opinion Research》1991,3(1):86-99

Non-response bias is of great concern in pre-election politicaltelephone polls, where the number of callbacks is far less thanin most academic and government studies. The fewer number ofcallbacks raises the issue of whether there might be a greaternon-response bias problem in such surveys. Given the publicimportance of political polls, there is a need to know somethingabout this. The general problem faced in trying to assess thisissue is that it is very difficult, if not impossible, to obtaininformation on non-respondents. There is an additional problemwith political polling in that there are few public studiesabout non-response in such polling. This study assesses non-responsebias for five pre-election political polls which used four callbackseach. The study is unique in that information is available forall respondents and non-respondents. The initial list of individualsto be called was taken from a computerized voter registrationlist which contains the age and sex of each registrant. Thenon-response bias associated with not-at-homes, bad numbers,and refusals is assessed. The results indicate that bad numbersand not-at-homes have different bias effects from refusals,but they offset each other to some degree in a situation oflimited callbacks. More callbacks may reduce bias associatedwith not-at-homes, but not the bias associated with bad numbersand refusals. We usually do not know how biased nonresponseis, but it is seldom a good assumption that nonresponse is unbiased(Flower, 1984, p. 51–2  相似文献