1

The American Community SurveyAn Update

Pamela KleinAmerican Community Survey Office

Washington Metropolitan Council on Governments

Cooperative Forecasting and Data CommitteeWashington, DC

January 9, 2007

2

Purpose of the ACS

• Collect detailed Census sample data every month instead of only once each decade

• Release tabulations of these data on a yearly basis

• Restructure and simplify the 2010 Census

3

Release schedule for the ACS Data Products

Data products are released in the year following the single-year or multi-year period in which data are collected.

4

2005 Geographic AreasType of Legal, Administrative, or Statistical Area

Number included in

2005 ACS for the United

States

Number included in 2005 ACS for Puerto

Rico

Percent of

All Such Areas

Nation 1 -- 100%

States (including DC and Puerto Rico)

51 1 100%

Census Regions and Census Divisions

13 -- 100%

Congressional Districts 436 1 100%

Urban/Rural State Components (excluding DC)

50 1 100%

Public Use Micro Data Sample Areas

2,071 30 100%

5

2005 Geographic AreasType of Legal, Administrative, or

Statistical Area

Number included in

2005 ACS for the United

States

Percent of

All Such Areas

Number included in 2005 ACS for Puerto

Rico

Percent of

All Such Areas

Metropolitan, Micropolitan and Combined Statistical Areas

612 58% 11 69%

Counties and Municipios 776 25% 12 15%

School Districts 995 7% 1 100%

Places 469 2% 7 3%

American Indian and Alaska Native Areas

15 2% -- --

Minor Civil Divisions 188 2% -- --

Other Geographic Areas 3,934 3% 24 53%

6

Sampling Error

• Sampling error occurs when estimates are derived from a sample rather than a census of the population.

• Standard error is an estimate of the precision of the estimates.

• The margin of error describes the precision of the estimate for a given confidence level and standard error.

• Tools used to prevent incorrect conclusions

7

Margin of Error

8

Statistical Significance

• Small differences may be insignificant.

• To do statistical testing of two estimates, you must calculate the standard error of the difference of the estimates.

• Two estimates are "significantly different" if their difference is large enough that there was a less than 10 percent chance that the difference was purely random.

9

Using ACS Data

• ACS data are comparable to Census 2000

• Comparing 2005 ACS data with 2004 ACS data

• Percentage distributions

10

Reference Materials

• ACS Data User Training Guide

• ACS Design and Methodology technical document

• Using Data From the 2005 ACS

http://www.census.gov/acs/www/

11

Data Products

• Detailed Tables • Data Profiles• Narrative Profiles• Ranking Tables• Thematic Maps• Geographic Comparison Tables• Subject Tables • Selected Population Profiles

12

http://factfinder.census.gov/home/en/acs_pums_2005.html

Public Use Microdata Sample (PUMS)

13

2005 User’s Guidehttp://www.census.gov/acs/www/Products/users_guide/index.htm

14

Thematic Maps

15

Data Profiles

16

Geographic Comparison Tables

17

Selected Population Profiles

18

Detailed TablesUsing the “options” tab, you can display information by different geographic components, such as urban and rural.

19

For More Information

American Community Survey Office1-888-346-9682

cmo.acs@census.govwww.census.gov/acs/www

U.S. DEPARTMENT OF COMMERCEU.S. Census Bureau

Washington, DC 20233

ACS Alerthttp://www.census.gov/acs/www/Special/Alerts.htm