As the Internet continues to grow as a medium for survey administration, research on internet surveys compared to more traditional methods such as paper and pencil, lags further behind. Further research on coverage, sampling,

measurement, and non-response error is needed. This study explores respondent differences between web-based surveys and paper/pencil surveys by comparing response rates, the demographic profile of respondents, and the

types of responses offered. The results from this study show no demographic differences between web-based respondents and paper/pencil respondents, which is primarily attributable to the college student sample. In addition, this study finds no difference in overall response rates on the web-based survey and the paper/pencil survey. However, the study did find that partial non response was higher for web-based surveys then for paper/pencil surveys, with fewer web-based survey respondents

completing the survey. Finally, it does appear as if the length of comments offered for open-ended items is higher in paper/pencil administration compared to web-based administrations. This study adds to the growing but limited body of research on web-based surveys. It suggests that issues related to coverage error, non response error, measurement error, and sampling error need continued efforts and that our understanding of the impact of these errors within a web-based modality is still limited.