Research highlights of the Consumer Expenditure Survey redesign
The CE program initiated the Gemini Project in early 2009. The mission of the project is to improve expenditure estimates in the CE Survey by reducing measurement error, particularly error generally associated with underreporting. Underreporting in the CE Survey occurs when respondents fail to report expenditures that they were instructed to report upon. A secondary goal of the redesign is to halt or reverse the decline in response rates while maintaining current production costs. The redesign project is motivated by concerns about both the quality of the current survey and the need to adapt to the changing circumstances in which the survey operates. In terms of data quality, evidence of measurement error has provided impetus for a new design. The ratio of aggregate expenditures measured by the CE Survey to the Personal Consumption Expenditures data from the Bureau of Economic Analysis has been declining, suggesting the presence of possible CE Survey underreporting.2 Examination of subgroup expenditures has revealed differences in amounts reported based on the mode of interview and whether records were used.3
Several other elements of the survey—complexity, potential conditioning in respondent behavior, proxy reporting, interview length, and recall error—also present obstacles to the accurate reporting of expenditures. Changes in the social and technological environment complicate the task of reducing measurement error, as these changes are increasingly important mechanisms through which measurement error may be introduced into the survey. For example, purchases made online or recurring bill payments made by automatic debit may be less salient to respondents. Flexibility in the CE Survey’s ability to modify data collection strategies to incorporate new questionnaire designs and multimode collection better positions the program to respond to such changes over the long term.
In terms of response rates, the CE program has noted a gradual decline in response to both the CEQ and CED in recent years. In 2000, the response rate was 81 percent for the CEQ and 77 percent for the CED (compared with 71 percent for both the CEQ and CED in 2011, as noted earlier). As a result, CE program staff are developing, testing, and evaluating design changes with the goals of improving overall data quality, increasing the analytic value of the data to users, and supporting greater operational flexibility to respond to changes in the data collection environment.
The changes being pursued through the Gemini Project will ensure that the CE Survey satisfies its primary purpose: maintaining the integrity of the expenditure weights used in the Consumer Price Index (CPI). Consumer expenditure data supplied by the CE Survey are a critical component of the CPI, as they are used to estimate weights for the CPI’s consumer goods and services classification structure used in the calculation of the CPI. In the construction of the CPI, four distinct functional uses of CE Survey data are made: (1) to estimate biennial expenditure weights, (2) to estimate monthly expenditure weights, (3) to calculate the probability that an item’s price will be included in the CPI calculations, and (4) to allocate expenditure estimates between more-broadly defined expenditure categories from other survey sources.4 Improved data quality also enhances the usefulness of the CE Survey data to other major data users, both public and private, in addressing topics such as consumption/inequality analyses and the measurement of poverty. Therefore, data quality improvements refer to aggregate estimates of total and mean expenditures as well as to the distribution of expenditures at the microdata level. Finally, increasing the flexibility of survey operations allows the program to meet new challenges associated with data quality in a timely fashion.
2 Thesia I. Garner, George Janini, William Passero, Laura Paszkiewicz, and Mark Vendemia, “The CE and the PCE: a comparison,” Monthly Labor Review, September 2006, pp. 20–46, http://stats.bls.gov/opub/mlr/2006/09/art3full.pdf.
3 Adam Safir and Karen L. Goldenberg, “Mode effects in a survey of consumer expenditures,” Statistical and Survey Methods Research Papers (U.S. Bureau of Labor Statistics, 2008), http://www.bls.gov/osmr/pdf/st080200.pdf.