The polling industry has come under considerable strain after the erroneous predictions of the US-American presidential election and the Brexit-referendum. Election polls need to be implemented within a short framework of typically just a few days, and thus quick and lean survey modes such as online access panels are often preferred. However, these panels generally use non-probability techniques, such as online advertising, to recruit panelists and to select survey participants. Some comparative studies have shown that the samples of such nonprobability online panels lack representativeness of the general population and lead to less accurate data than traditional probability-based offline surveys. Our study assesses the effect of survey sampling and survey mode on the samples’ suitability for studying social and political phenomena in both cross-sectional and longitudinal research. To assess sample suitability for cross-sectional research, we evaluate the accuracy and response quality of eight nonprobability online samples, two probability-based online samples, and two probability-based face-to-face samples. All samples were specifically drawn to be representative of the general population aged 18 to 70 in Germany in 2015. To assess sample suitability for longitudinal research, we evaluate retention rates for three waves of data collection conducted at half-year intervals in all online samples.
Presented by:
Annelies Blom, University of Mannheim
Date & time:
March 12, 2018 4:00 pm - March 12, 2018 5:30 pm
Venue:
2N2.4.16
External seminars home