|
Title
|
|
Methodological Issues in Local Area Application of the American Community Survey
|
|
Date / Time / Room
|
Sponsor
|
Type
|
08/14/2002
2:00 PM -
3:50 PM
Room: H-Regent Parlor
|
Section on Government Statistics*, Section on Survey Research Methods*, Social Statistics Section*
|
Invited
|
|
Organizer:
|
Leonard M. Gaines, Empire State Development
|
|
Chair:
|
Leonard M. Gaines, Empire State Development
|
|
Discussant:
|
3:20 PM - Charles Alexander, U.S. Census Bureau
3:35 PM - Susan P. Love, U.S. Census Bureau
|
Description
The American Community Survey (ACS) is designed to provide current data, similar to that included on the decennial census long-form, for areas as small as census tracts on an annual basis using moving averages of different lengths based on the area's population. Having local area data issued more often than once a decade, with a lag that may make the decennial data 12 years out of date, is a major boon to local area analysts. However, there are a number of methodological issues that greatly impact the usefulness and interpretation of the data produced by this survey. Examples of the issues raised by this survey's design include: (1) how do you compare estimates based on moving avergaes of different lengths, (2) how can high quality population and housing unit controls be produced, (3) how do differences in the control estimates affect the survey estimates charateristcs, and (4) how can these survey statistics be used with local program administartive records. This session will explore these and other issues realted to the use of the ACS for local areas.
|
|
