Skip to main content

Integrating Survey and Non-survey Data to Measure Behavior and Public Opinion?

Surveys have long been the primary source of data collection about peoples’ attitudes, beliefs, and opinions and are useful for measuring specific information about individuals, as well as understanding public opinions and creating accurate and precise official statistics.  Over the past few years, artifacts of our increasingly digital lives have offered additional, broader information about our behaviours (e.g., purchase histories, personal interests captured through internet browsing) in the form of “big data”.  These two sources of information have great potential to complement one another to allow scientists to better understand people and the world in which we live, for instance by combining the low cost per data point of big data (offsetting the rising costs of survey-based data collection) with the ability to collect very specific information addressing research questions using survey data. In this collection, we present the state-of-the-art in research at the intersection of these two approaches to data collection and analyses, exploring important issues pertaining to their combination and use in the social and data sciences.

Relevant topics include:

  • practical applications for combining survey and big data sources to improve the quality of statistics production,
  • the insights afforded by data science and machine learning and how they can complement traditional statistical analyses,
  • considering the effects of sampling of individuals within populations vs. the implications of “N=all” from big data sources, 
  • improving questionnaire administration using artificial intelligence (AI),
  • developing survey questions based on big data sources or samples,
  • automation of survey data processing or coding using methods from AI,
  • and applying the Total Survey Error/ Total Data Error paradigm to adopt a total statistical uncertainty framework that will be needed to encompass the new quality issues associated with big data: Total Error (Biemer, 2017)

Lead Guest Editor:

Antje Kirchner, RTI International, University of Nebraska - Lincoln, USA 
 
Guest editors:   
Trent Buskirk, Bowling Green State University, USA  

Ingmar Weber, Hamad Bin Khalifa University, Doha, Qatar
 
Nan Zhang, American University, USA 
  

  1. Combining survey data with alternative data sources (e.g., wearable technology, apps, physiological, ecological monitoring, genomic, neurocognitive assessments, brain imaging, and psychophysical data) to paint...

    Authors: Charles E. Knott, Stephen Gomori, Mai Ngyuen, Susan Pedrazzani, Sridevi Sattaluri, Frank Mierzwa and Kim Chantala

    Citation: EPJ Data Science 2021 10:9

    Content type: Regular article

    Published on: