Internet penetration is increasing worldwide. Currently nearly 80% of North Americans use the Internet. To gather information about a large population, it is becoming increasingly attractive to use the Internet as a method of data collection. A number of national surveys conducted in the United States, such as the Behavioral Risk Factor Surveillance Survey (BRFSS), traditionally have used the telephone as the data collection methodology. However many national surveys, such as BRFSS), have explored the Internet as an option to collect probability data in the United States and elsewhere; e.g. Jackle et.al. (2010) discuss the use of Internet data collection for the European Social Survey. With the increasing use of the Internet to collect survey data, it is important to compare data collected by traditional methods with data collected using the Internet. Bethlehem (2010) describes some methodological problems associated with Internet surveys. Studies to investigate strategies that maximize response rates but do not introduce additional bias from Internet responses are particularly necessary. A series of experiments were conducted in probability-based surveys in Oregon from 2006 through 2010 to identify features that improved response rates using the Internet. Responses to questions, and the demographics of individuals who chose to response by the Internet, are compared to data collected by the more traditional approaches. Factors that were investigated in these studies included the level of detail to include in the instructions on gaining Internet access to the questionnaire and whether providing a choice of using the Internet or forcing a respondent to complete the questionnaire by Internet provided higher response rates. Finally, response rates with a varying number of contacts are assessed.

References:

Bethlehem, J. (2010). Selection Bias in Web Surveys. International Statistical Review, 78(2), 161–188.

Jackle, A., Roberts C., P. Lynn. (2010). Assessing the Effect of Data Collection Mode on Measurement. International Statistical Review, 78(1), 3–20.

Keywords: Internet; Mixed-mode surveys; Response rates

Biography: Dr. Lesser is a Professor in the Department of Statisticis at Oregon State University. She also is the Director of the Oregon State University Survey Research Center. Her research interests include survey methodology and nonresponse in sample surveys.