From the Total Survey Error Framework to an Error Framework for Digital Traces of Humans
Explore the evolution from the Total Survey Error Framework to an Error Framework for Digital Traces of Humans in this comprehensive tutorial presented at FAT*2020. Delve into the challenges of adapting survey methodologies to digital data analysis, covering topics such as survey guidelines, digital traces, and the intersection of computer science and social science. Learn about key concepts including target populations, signals, entities, measurement, representation, and sampling. Examine the rationale behind using the Survey Error Framework and investigate its limitations when applied to digital traces. Gain insights into natural experiments, coverage error, entity selection error, data preprocessing, and analysis techniques. Enhance your understanding of how to effectively work with and interpret digital traces of human behavior in research and data science applications.