Online versus phone surveys: comparison of results for a bicycling survey

摘要

Researchers in the transportation field rely heavily on traditional random-digit-dialing phone surveys and increasingly on online surveys. Many studies have looked at the strengths and weaknesses of the two methods, but few have examined differences in the inferences that can be drawn from the data generated by the two survey methods. In this paper, we compare both descriptive and inferential results from online and phone surveys with identical questions conducted in Davis, California. Results show that although bicycling behavior does not differ across the two survey samples, many socio-demographic characteristics do. The models developed from each sample have several statistically indistinguishable coefficients but also notable differences in key explanatory factors. The results suggest that online and phone survey methods have the potential to produce significantly different results, both descriptively and inferentially.