temporal, spatial, and demographic patterns of interest from a data set as large as the ACS (see, e.g., National Research Council, 2001:App. B). In turn, the ability to more readily identify data quality patterns should facilitate planning for in-depth research and evaluation to identify ways to improve the ACS.

Recommendation 7-7: The Census Bureau should develop and publish an ongoing quality profile for the ACS to inform users of the survey’s data quality, to guide the development of a continuing program of data quality assessments, and to identify areas for survey improvement. The Census Bureau should seek input from users on priority topics for assessment and design reports that they would find to be useful additions to the technical reports.

BOX 7-2

2006 and 2007 American Community Survey Methods Panels

“Methods panel” is a term used by the Census Bureau to refer to samples of households that are used for testing and experimentation for a continuing household survey. For the ACS, the Census Bureau fielded a 2006 methods panel (see Federal Register, vol. 70, no. 45, March 9, 2005: 11609-11610). It is planning to field a 2007 methods panel later in the year (see Federal Register, vol. 71, no. 94, Tuesday, May 16, 2006:28302-28305).

2006 ACS Methods Panel

The 2006 ACS Methods Panel (also known as the 2006 ACS Content Test) was designed to test new questionnaire content to be considered for inclusion in the ACS in 2008 and modification of existing content to improve response. The test included four stages:

  1. Determination, with input from federal agency stakeholders, of eligible content for the test.

  2. Cognitive laboratory pretesting, expert reviews, and other methods to develop alternative versions of the eligible questions. Eleven of 25 existing housing questions, 15 of existing population questions, and 3 new population questions were identified for inclusion in stage 3.

  3. National sample field test of about 50,000 housing unit addresses. About half the sample served as the control panel, receiving the existing ACS questionnaire; the other half served as the test panel, receiving alternative versions of the questionnaire. Mailed out to all sample addresses were advance letters, questionnaires, and reminder postcards, followed by second questionnaires to

The National Academies | 500 Fifth St. N.W. | Washington, D.C. 20001
Copyright © National Academy of Sciences. All rights reserved.
Terms of Use and Privacy Statement