Chapter

Using Scanner Data to Improve the Quality of Measurement in the Consumer Price Index

William J. Hawkes and Frank W. Piotrowski

in Scanner Data and Price Indexes

Published by University of Chicago Press

Published in print February 2002 | ISBN: 9780226239651
Published online February 2013 | e-ISBN: 9780226239668 | DOI: http://dx.doi.org/10.7208/chicago/9780226239668.003.0002
Using Scanner Data to Improve the Quality of Measurement in the Consumer Price Index

More Like This

Show all results sharing this subject:

  • Econometrics and Mathematical Economics

GO

Show Summary Details

Preview

This chapter employs scanner data for price measurement of ice cream. Using scanner or other electronic point-of-sale (EPOS) data in consumer price indexes (CPIs) produce more data and, consequently, less variance, better data and, consequently, less bias, as well as better methods. Scanner data offer a veritable library of information relating to individual item elasticities and cross-elasticities. Direct adjustment, manufacturer's cost adjustment, hedonic adjustment, and characteristic-based subgroups are employed to adjust the quality changes in the CPI framework, or the quality differences in an inter-area price comparison framework. One of the thirty-four “scannable edible” item strata for which separate price indexes are computed in the CPI is “ice cream and related products.” Dividing “ice cream and related items” into four separate modules would lead in a moderate reduction in variance in measuring year-to-year change at the item stratum level, since the subgroups differ among themselves in their year-to-year change.

Keywords: scanner data; consumer price index; price measurement; ice cream; direct adjustment; cost adjustment; hedonic adjustment

Chapter.  8243 words. 

Subjects: Econometrics and Mathematical Economics

Full text: subscription required

How to subscribe Recommend to my Librarian

Users without a subscription are not able to see the full content. Please, subscribe or login to access all content.