On the Accuracy of Nielsen Homescan Data
by Liran Einav, Ephraim Leibtag
, and Aviv Nevo
Economic Research Report No. (ERR-69) 34 pp, December 2008
Researchers use Nielsen Homescan data, which provide detailed food-purchase information from a panel of U.S. households, to address a variety of important research topics. However, some question the credibility of the data since the data are self-recorded and the recording process is time-consuming. Matching purchase records from 2004 Homescan data with data obtained from a large grocery retailer, it is evident that quantities purchased are reported more accurately in Homescan than are prices. Many of the price differences may be driven by the way Nielsen imputes prices: when available, Nielsen uses store-level prices instead of the actual price paid by the household. There are also differences by household type in the tendency to make mistakes that are correlated with demographic variables. However, the fraction of variance explained by the documented recording errors is in line with other research data sets for which cross-validation studies have been conducted.
Keywords: Nielsen, Homescan, scanner data, validation study
In this publication...
- Report summary, 99 kb | HTML
- Abstract, Contents, and Summary, 128 kb
- Introduction, 26 kb
- Data Sources, 26 kb
- Data Construction, 32 kb
- Record-Matching Strategy, 155 kb
- Do the Differences Matter?, 29 kb
- Conclusions, 25 kb
- References, 23 kb
- Entire report, 356 kb
- Download ERR69.zip, 432 kb
Need help with PDFs?