Elsevier

Preventive Medicine

Volume 53, Issues 4–5, October–November 2011, Pages 274-277
Preventive Medicine

Non-response bias in a web-based health behaviour survey of New Zealand tertiary students

https://doi.org/10.1016/j.ypmed.2011.07.017Get rights and content
Under a Creative Commons license
open access

Abstract

Objective

There has been little investigation of non-response bias in web-based health surveys. We hypothesised that non-respondents have a higher prevalence of risk behaviours than respondents.

Method

In 2005, random samples of students aged 17–25 years from 12 New Zealand tertiary institutions (n = 7130) were invited to complete a web-based health behaviour survey, with three e-mail reminders. Early respondents (before 2nd reminder) were compared with late respondents (after 2nd reminder). Late respondents served as a proxy for non-respondents.

Results

2607 students (37%) responded early, 676 (9%) responded late, and 3847 (54%) did not respond. There were differences between early and late respondents in high school binge drinking (38% vs 47%, p = 0.002) and non-compliance with physical activity guidelines (12% vs 18%, p = 0.004). Differences in overweight/obesity (26% vs 31%, p = 0.058), smoking (18% vs 22%, p = 0.091) and non-compliance with dietary guidelines (76% vs 77%, p = 0.651) were non-significant but point estimates were in the expected direction. Estimated bias in prevalence of risk behaviours was an absolute difference of 1–4% and a relative difference of 0–21%.

Conclusion

Respondents whose participation was hardest to elicit reported more risk behaviour. Assuming non-respondents' behaviour is similar or more extreme than that of late respondents, prevalence will have been substantially underestimated.

Highlights

► We investigated non-response bias in a college web-based health behavior survey. ► Late respondents were more likely than early respondents to report unhealthy behaviour. ► Non-response bias appeared to vary by health behavior and gender. ► Post-weighting to the population to adjust for non-response probably introduces error.

Keywords

Internet
Web
Survey
Health
Risk behaviour
Non-response
Bias

Cited by (0)

Sources of support: Health Research Council of New Zealand and Alcohol Advisory Council of New Zealand.