Respondents of a follow-up web-based survey
Methods: Data are from a survey of adults conducted in 2013-14. The web component was sent to eligible telephone survey respondents (completed the phone survey in English, reported recent internet use, agreed to be re-contacted, and provided a valid email address). Both surveys were conducted by Westat, a research firm headquartered in Rockville, MD. Among 4,186 telephone respondents, 1,176 were eligible and invited to take the web survey (web survey response rate = 41.0%). We compared characteristics of respondents eligible for and completing the web survey (N=482), relative to the telephone survey.
Results: Relative to telephone survey respondents, those eligible for the web survey were more likely to be male (47% versus 41%); non-Hispanic White (67% versus 58%), college graduates (68% versus 45%), have household incomes of $75,000 or more (57% versus 45%), US born (73% versus 65%), and younger (mean age, 55 versus 59). Web respondents did not differ substantially by gender from telephone respondents (43% versus 41% for males), but were even more likely to be White (82% versus 58%), college graduates (75% versus 45%), have household incomes of incomes of $75,000 or more (66% versus 45%), and US born (84% versus 65%). Unlike for eligibility, the mean age was similar (both age 59).
Conclusion: Unlike previous studies, we found that web survey respondents in an area with high internet access were only slightly more likely to be male but they were of similar age to RDD telephone survey respondents, even though these groups were more likely to be eligible. However, web survey respondents were more likely to be White, well-educated, higher income, and US born. These biases were even more pronounced for those who completed the web survey versus those who were eligible.
Assess whether or not demographic biases are evident between respondents of a web survey and respondents of a random digit dial telephone survey in an area with high internet access.
Keyword(s): Epidemiology, Survey
Qualified on the content I am responsible for because: I am an epidemiologist with graduate training in public health and epidemiology. My work experience includes survey research.
Any relevant financial relationships? No
I agree to comply with the American Public Health Association Conflict of Interest and Commercial Support Guidelines, and to disclose to the participants any off-label or experimental uses of a commercial product or service discussed in my presentation.