American Community Survey (ACS)

Skip Navigation Menu for Past Notices on ACS

Notice About Using the 1999 American Community Survey Estimates

Special Limitations of the 1999 American Community Survey Estimates

Significant Changes from 1998 to 1999

Significant Changes from 1998 to 1999

Data Collection

Questionnaire Changes

The 1999 American Community Survey questionnaire was changed to be consistent with the content of the Census 2000 long form. We dropped questions that were no longer a requirement for Census 2000, and added questions such as the grandparents as caregivers series. We also reworded questions to conform with the wording of Census 2000 questions. These changes will facilitate the American Community Survey and Census 2000 comparisons.

Group Quarters

For the 1999 American Community Survey, we selected not only a sample of housing units, but a sample of Group Quarters (GQs), and then a sample of persons within the GQs. Most types of GQs are included in the sample and in the appropriate estimates for the first time in 1999. No separate estimates are produced for GQs, they are only included in totals. The sample was selected from the 1990 census GQ inventory. No GQs have been added to the inventory since then and many of the GQs in the inventory have moved or no longer exist. Only GQs that still exist at the same address are included in the estimates.

Data Processing

Editing and Allocation

The edit and allocation system was modified for several reasons:

• to account for changes to the questionnaire, including the introduction of new variables,
• to account for changes in the standard code lists for coded variables,
• to more closely match the edit and allocation system used to process the Census 2000, and
• to expand the definition of allocation flags.

Weighting

Two changes in the weighting procedure have been made for 1999 American Community Survey. The first change is because of inclusion of GQs in the sample. The population estimates to which we adjust in the calculation of the factor PPSF include GQ as well as housing unit population. The second change is that the number of housing units in each tract is not controlled to Master Address File (MAF) counts (MAF1, MAF2) as it was previously. This is because the number of addresses on the MAF has been constantly changing due to Census 2000 operations which are adding and removing addresses.

As a result, for counties that were also in 1998 American Community Survey there may be a noticeable difference in total housing units when comparing 1998 and 1999. Other housing unit estimates may also show a difference due to this weighting change. In most cases it is difficult to determine whether such differences are due to the change in weighting or sampling variability.

Data Products

The 1999 American Community Survey is part of the Census comparison phase of this project. Therefore, the Census Bureau is striving to make the American Community Survey data products as similar as possible to the corresponding Census 2000 data products. Detailed summary tables for 1999 American Community Survey sites are posted on the American FactFinder website.

[PDF] or denotes a file in Adobe’s Portable Document Format. To view the file, you will need the Adobe® Acrobat® Reader available free from Adobe. This symbol indicates a link to a non-government web site. Our linking to these sites does not constitute an endorsement of any products, services or the information found on them. Once you link to another site you are subject to the policies of the new site.