Coverage Error Embedded in Self-Selected Internet-Based Samples: A Case Study of Northern Indiana

The Internet is rapidly evolving as a new tool for conducting tourism research. Given known advantages, steps to examine the possible drawbacks need to be taken to verify Internet survey methods. This article focuses, in particular, on coverage error of self-selected e-samples. Based on the response to a question regarding willingness to provide contact information on the Internet, the respondents of two conventional tourism surveys were assigned to likely, somewhat likely, and not likely groups. Analyses were conducted to identify differences between these groups in terms of demographics, travel styles, travel-planning behaviors, and trip characteristics. The results indicate that Internet-based sampling procedures create a substantial potential for bias. Therefore, use of the Internet for tourism research requires substantial caution when generalizing the findings to a population that includes nonusers and self-selected nonparticipants.