Social Media, Web, and Panel Surveys: Using Non- Probability Samples in Social and Policy Research

The use of online surveys has grown rapidly in social science and policy research, surpassing more established methods. We argue that a better understanding is needed, especially of the strengths and weaknesses of non-probability online surveys that can be conducted relatively quickly and cheaply. We describe two common approaches to non-probability online surveys – river and panel sampling – and theorize their inherent selection biases: topical self-selection and economic self-selection. We conduct an empirical comparison of two river samples (Facebook and web-based) and one panel sample (from a major survey research company) with benchmark data grounded in a comprehensive population registry. We examine (1) how closely the online samples correspond with the benchmark, and (2) their usefulness in studying a non-demographic subpopulation. The river samples diverge from the benchmark on demographic variables and yield much higher means on non-demographic variables, even after weighting; we attribute this to topical self-selection. The panel is closer to the benchmark. When examining the characteristics of a non-demographic subpopulation, we detect no differences between the river and panel samples. We conclude that non-probability online surveys don’t replace probability surveys, but augment the researcher’s toolkit with new digital practices, such as exploratory studies of small and emerging non-demographic subpopulations.