Comparing data quality between online panel and intercept samples

• Main Author: Mingnan Liu
• Format: Article
• Language: English
• Published: SAGE Publishing 2016-10-01
• Series: Methodological Innovations
• Online Access: https://doi.org/10.1177/2059799116672877

Although some research effort has been devoted to the comparison of probability- and nonprobability-based Web surveys, different types of nonprobability-based samples have not been thoroughly examined. This exploratory study compares the data quality between online panel and intercept samples. Online panel refers to a pre-recruited and profiled pool of respondents. An intercept sample is a pool of respondents that are obtained through banners, ads, or promotions. Anyone can click on them and subsequently respond to a survey. Respondents are not pre-recruited or profiled. Three surveys with 52, 29, and 19 questions, respectively, were administered to both samples. Propensity score weighting adjustment is used for the analyses. The results show that the completion rates are higher for the panel than the intercept sample. The completion times are similar for these two samples. Data quality, on average, tends to be higher for panel than intercept samples.