Attachment A - Bounding Interview Elimination

Bounding Interview Elimination

Beginning in January 2015, and coinciding with the implementation of the 2010 Sample Design, the Consumer Expenditure (CE) Interview Survey will eliminate the first wave bounding interview. The CE Interview Survey will be a four wave, or panel, survey. All four waves will have a three month reference period and data from all waves will be used in the final, published data.

The CE Interview Survey currently consists of five waves/panels, the first of which serves as the bounding interview. The expenditure data collected in the first wave bounding interview is different than the expenditure data collected in the four subsequent waves. The bounding interview reference period is one month; the subsequent waves have a three month reference period. Additionally, expenditure data collected in the bounding interview are not included in the final, published expenditure data. Substantial research has been done on the effectiveness of the bounding interview, and its impact on data quality and respondent burden. See Attachment A (i) “Recommendation Regarding the Use of a CE Bounding Interview” (Elkin, 2013). After considering this research, BLS has decided to eliminate the bounding interview in the CE Interview Survey, and introduce the new four wave structure beginning with the phase-in of the 2010 Sample Design

Sample Redesign

In previous sample redesigns, additional sample was needed in introducing CUs into the sample from new PSU’s because a bounding interview was conducted. For example, a new PSU case would complete a bounding interview in November and then complete their second wave interview in February. Neither expenditure data from that bounding interview, nor any expenditure data from November or December, which was collected in the February interview, would be included in final published expenditure data. However, in the introduction of the 2010 Sample Design, that additional sample is not needed. New PSU cases will be introduced beginning in February 2015, and will be in the Interview survey for four waves, with no bounding interview.

In the dropped and continuing PSUs, the final bounding interviews will occur in December 2014. The CUs which have a bounding interview in December 2014 will still have their next interview in March 2015 and the interview will have a three month recall.

Related Bounding Interview Research and Findings

“Recommendation Regarding the Use of a CE Bounding Interview” (Elkin, 2013) – Attachment A (i)

Given evidence that the bounding interview may not be effective in minimizing telescoping errors, and since its expenditure data are not used for publication or microdata purposes, eliminating it from the series of panel interviews is one method of reducing data collection costs without adversely affecting the quality of the data. The purpose of this report is to present 1) findings from research into eliminating the bounding interview, 2) an estimate of the net impact on length and cost from eliminating the bounding

interview, 3) additional research options for determining bounding interview impact, 4) methods proposed to address the potential for higher burden associated with adding the roster and inventory items to the second interview, and 5) a consensus recommendation regarding the elimination of the bounding interview from the CEQ Interview Survey.