What is survey post-stratification for offline and online surveys?

Speaker(s):

Marco Pomati, Q-Step Centre, School of Social Sciences, Cardiff University

Abstract:

Survey post-stratification is a technique used to ensure that your sample accurately reflects the characteristics of the target population in terms of key demographic or other relevant variables. It involves using data from a reliable external source, such as a census, to construct a set of weights which are then applied to the survey data to adjust for any imbalances in the sample. If done properly, it can improve the accuracy of survey results by reducing bias and increasing representativeness. In brief, post-stratification weights are used in most surveys. If you have collected your own survey, you may want to consider constructing post-stratification weights. Similarly, whether you are analysing your own or secondary data, you may want to understand why and how these weights are constructed and how you should integrate them when reporting simpler and more complex results from your analysis.