Chapter 16.
Consumer Expenditures and Income

Evaluation Research
The surveys undergo continuous evaluation by comparing Consumer Expenditure Survey results with other data and by performing internal statistical analyses to address current concerns. To improve the expenditure estimates, research related to the data collection instruments and statistical studies of underreporting began in the mid-1980s. As a result of this research, investigations into the cognitive aspects of the data collection process became standard. A separate branch was established within the Division of Consumer Expenditure Surveys in 1999 with the mission of conducting methodological studies to improve survey instruments and field collection procedures. Recent research has placed an emphasis on developing alternative questionnaire formats and question phrasing and on approaches to maintaining or increasing response rates. Attention has also been focused on the demands placed upon respondents’ time.

The new user-friendly diary form, introduced in 2005, is an example of research into alternative questionnaire formats. The new diary is the culmination of an extensive series of studies, including a large-scale field test. Through group discussions with data collection staff and cognitive testing with respondents, researchers learned that respondents preferred a more open format. The diary now obtains purchase data in four general categories, rather than the numerous detailed subcategories used previously. Another major improvement was the addition of checkboxes to collect data about meals eaten away from home, eliminating the need for respondents to provide this information. Checkboxes have the added benefit of facilitating data coding, and so contribute to streamlined processing. While the new instrument is more efficient, it is also visually more appealing, as it is physically smaller, contains fewer pages, and is printed in brighter colors than its predecessor. An evaluation of the new form showed that it was generally effective, and demonstrated marked improvements in collection of some types of expenditures.

Ongoing research has focused on a variety of issues aimed at reducing respondent burden and improving the quality of survey data. Research studies underway include: examining the effect of incentives on response rates and data quality; investigating the dimensions of nonresponse bias; collecting and analyzing supplemental information about the survey (“paradata”) such as data from the Contact History Instrument, which may shed light on improvements to field procedures; and ways to increase within-household participation in the Diary Survey. Research results have been presented at the annual conferences of the American Association for Public Opinion Research and the American Statistical Association (ASA), and papers from both conferences can be found in the ASA Conference Proceedings.

Next: Uses and Limitations