Webcast: Improving the Accuracy of Marketing Survey Data with New Statistical Approaches
Advertisers, media companies, and market researchers are seeking cost-effective consumer survey approaches that can take advantage of the scientific rigor of probability sampling while leveraging the scale of inexpensive non-probability, opt-in online samples.
This webinar addressed how traditional probability and non-probability samples can be combined to upgrade the accuracy of information collected from opt-in online surveys. TrueNorth®, an innovative statistical approach developed by NORC at the University of Chicago has been successfully applied to high-profile projects such as AP VoteCast, which provided major news organizations accurate estimates of the vote as they declared winners in the 2018 midterm elections.
Key Takeaways:
- NORC’s TrueNorth approach for combining probability and non-probability samples can provide cost effective and reliable survey data to inform business decisions.
- TrueNorth calibration methodology uses small area models to leverage information from the probability sample and reduce potential bias in the non-probability sample.
- TrueNorth utilizes the scale of the non-probability sample to provide more precise estimates for key demographic subgroups or hard-to-reach groups.
- Inclusion of probability sampling and calibration weighting assures accuracy in market research surveys.
Presented by
Ipek Bilgen, Senior Research Methodologist, NORC at the University of Chicago
David Sterrett, Senior Research Scientist, NORC at the University of Chicago
View Video: