When survey science met online tracking: presenting an error framework for metered data

RECSM Working Papers Series, 62, 2021

Recommended citation: Bosch, O.J., and M. Revilla (2021) When survey science met online tracking : presenting an error framework for metered data. http://hdl.handle.net/10230/46482 https://www.upf.edu/documents/3966940/6839730/WP62.pdf/16aaf443-c545-2f5a-faac-a2bb55dec4d6

Abstract: Metered data (also called “web log data” or “web-tracking data”) is a type of data obtained from a meter willingly installed by participants on their devices. A meter refers to a heterogeneous group of technologies that allow tracking, at least, information about the URLs of the web pages visited. Metered data has the potential to replace part of survey data or to be combined with survey data to obtain higher quality data. It is crucial, nevertheless, to understand its limitations to mitigate potential errors. Although some research has explored some potential error causes a systematic categorization and conceptualization of these errors is missing. We present a framework of all errors that can occur when using metered data. We adapt the Total Survey Error framework to accommodate it to the specific error generating processes and error causes of metered data. The adapted error framework shows 1) the data collection and analysis process of metered data and 2) how the unique characteristics of metered data can affect data quality. This framework can be useful to choose the best design options for metered data, but also to make better informed decisions while planning when and how to supplement or replace survey data.

Check paper here