ACS Data Collection and Processing Methods
2005 ACS Special Product for the Gulf Coast Area
This documentation provides users with a basic overview of the American Community
Survey (ACS) data collection methods and procedures that were used for this special
product. It also provides a general overview of the data capture and processing activities.
DATA COLLECTION METHODS
The ACS selects a random sample from the Census Bureau’s file of housing unit
addresses. An address has about 1 chance in 480 of being selected for participation in the
ACS in any month. No address will be selected more often than once every five years.
Each year, the ACS includes 12 independent samples, with a new sample introduced each
month. Data collection for each sample lasts for three months, and uses three modes of
Data collection starts with the mail phase, which includes mailing a prenotice letter, an
initial questionnaire package four days after the prenotice letter, and a reminder postcard
three days after the questionnaire package to the sample addresses. Approximately three
weeks later, ACS mails a replacement mailing package to those addresses which have not
returned the initial questionnaire.
In the areas most impacted by the hurricanes, ACS did not mail a replacement mailing
package to the September sample addresses. For the October sample, ACS delayed or
did not mail any of the mailing pieces. For the November sample, the ACS resumed the
standard mail procedures. Note that ACS modified the prenotice letter starting with the
October sample, and modified the reminder card and the letters sent with the two mailing
packages starting with the November sample. These modifications clarified to
respondents that they should be included on the ACS questionnaire if they were displaced
from their home due to Hurricane Katrina and now living at a sample address.
The second data collection phase is the computer assisted telephone interview (CATI)