What We Now Know About "I Don't Knows"

Abstract

A perennial problem facing survey researchers is what to do with "don't know" and "no opinion" responses. For the kindred problems of "nonresponse" (refusals and "not at homes") and "not applicable" codings, commonly accepted guidelines have evolved. But no guidelines exist for handling "don't know" and "no opinion" responses. One of the reasons for this is that little systematic investigation of the problem has been made. Instead, each researcher has been left to make individual assumptions about the nature of the responses and/or their distribution.This study focuses on an investigation of the assumption of randomness in nonresponse. The research results presented below suggest that it is invalid. Aggregate distributions provide only the weakest evidence for (or against) the hypothesis of randomness. Better evidence is obtained by determining whether a nonsubstantive response is systematically related to respondent attributes or to characteristics of the data-gathering procedure. Also, the aggregate distribution argument misses the point of the effects of hypothesis testing. Hypotheses tested by survey analysts seldom involve the full set of items in their questionnaires. If nonsubstantive responses are systematic and if a large number appear for the set of items employed for testing the hypothesis, these nonsubstantive responses (NSRs) are going to have some kind of systematic effect on the test if they are treated inappropriately. PRIOR RESEARCHIn his analysis of item nonresponse to a mail questionnaire, Ferber provided evidence to suggest nonrandomness. 1 He demonstrated that item nonresponse is systematically related to sex, age, education, and household composition. 2 In addition, he found statistically significant relationships at the .01 level between the index of item nonresponse and region, city size, and occupation.Regarding systematic relationships between NRSs and data-gathering procedures, Ferber indicated a relationship between the type of question asked and frequency of nonresponse.' On the other hand, he did not find

Attitudes Toward Surveys, Attitude Accessibility and the Effect on Respondents’ Susceptibility to Nonresponse

“…Data from presidential election studies has been tested as to whether the respondents' political involvement and their self-perceived political efficiency predicts the probability of insubstantial answers to questions about political issues (Francis and Busch, 1975). Both factors can be assumed to increase the cognitive availability of political opinions and were indeed found to reduce nonresponse.…”

Public Awareness and Performance Relating to the Implementation of a Low-Carbon Economy in China: A Case Study from Zhengzhou

“…For example, mechanisms that address an individual's internal motivations for inaction or poor environmental behaviour might be helpful [1,22], such as market-based mechanisms or economic tools. According to this study and others [26,30,31] the general public is willing, for example, to switch to a more fuel-efficient car or to retrofit their home with solar energy when en-couragement incentives (e.g. green subsidies, grants, funds and reward schemes) are available.…”

A NCaRBS analysis of SME intended innovation: Learning about the Don’t Knows

“…As contrasting slightly with Francis and Busch (1975). That is, with more education (higher education attainment), there is more focus on a substantive response.…”

“…In terms of analysing such uncertainty, Francis and Busch (1975) suggest, generally, which respondents with non-substantive responses, such as DK, should not be excluded from analysis, arguing such responses are not random and so exclusion would introduce bias in any undertaken analysis. The general limited investigation of the DK response problem, considered a vexing problem to researchers (Feick, 1989), with the slight exception of within the area of political opinion (Feick, 1989;Gilljam and Granberg, 1993; Lee and Kanazawa, 2000; Luskin and Bullock, 2011), may be due to the lack of technical approaches able to pertinently investigate this problem.…”