Census Data for Community Research

1

Census Data for

Community Research

HorizonsMoses Lake, Washington

March 20, 2010

Rural Reflections

Census Bureau Data Sources• General demographic data for community

profiles – counts of population (by age, sex, race, ethnicity) and housing■ Decennial Census■ Population Estimates Program

• Population and housing characteristics for needs assessments in grant proposals■ American Community Survey■ Other surveys and programs

2

What’s Available Online

• Census Bureau programs• Decennial Census• Population Estimates Program• American Community Survey• Economic Census / Surveys

3

Data are available online

through data access tool:

American FactFinder

www.census.gov

4

Census Bureau Home Pagehttp://www.census.gov

Other Surveys

5

Why Decennial Census Is Done• Political representation

■ Apportionment of 435 seats in the House of Representatives■ December 31, 2010: State population counts to President

■ Redistricting■ April 1, 2011: Redistricting data (population, voting age,

race, ethnicity totals) by census block to governors

• Distribution of Federal funding Over $400 billion allocated per year

Planning at state and local levels

6

Decennial Census• Taken every 10 years since 1790• Largest domestic undertaking in U.S.• Provides official counts of population

and housing down to block level• Reference date is April 1• Same form in 2010 to every household• Participation is mandatory• Workers take lifetime confidentiality oath

7

8

Census 2000 Questionnaire& Data Products

• 2000 “short” form - - basic questions■ Produced “100% data” or “counts”■ Data released down to block level■ Summary Files 1 and 2 (SF-1 and SF-2)

• 2000 “long” form - - same basic questions as “short” form, plus detailed questions - - sample was 1 in 6 U.S. households■ Produced “sample data” or “characteristics”■ Data released down to block group level■ Summary Files 3 and 4 (SF-3 and SF-4)

99

2010 Census QuestionnaireTopics

• (Name)• Sex• Age• Date of birth• Ethnicity

• Race• Relationship of people

within household• Rent / own house

(tenure)

Takes an average household ten minutes to complete

10

2010 Census Ethnicity Question

2010 Census Race Question

Census Geography:Hierarchy

Census Geography:Sub-County Relationships

2010 Census Data Release Schedule

14

Population Estimates Program• Official counts in inter-censal years

■ Developed with assistance of states: FSCPE – Federal State Cooperative for Population Estimates

■ 100% data released down to place level■ Uses:

– Federal funding allocations– Survey controls– Denominators: vital rates / per capita time series

• Reference date is July 1

15

Population Estimates Main Page

16

American Community Survey - ACS• Provides characteristics of population• Questions similar to 2000 “long form”• Participation is mandatory• 250,000 households in survey / month (or

3 million / year)• Covered every county in U.S. in 2005• First data releases dependent on

population thresholds – After first release, data released every year

17

18

19

19

American Community Survey Social Characteristics

• Education• Marital Status• Fertility• Grandparent Caregivers• Veterans• Disability Status

• Place of Birth• Citizenship• Year of Entry• Language Spoken at Home• Ancestry / Tribal Affiliation

20

20

American Community Survey Economic Characteristics

• Income• Benefits• Employment Status• Occupation• Industry• Commuting to Work• Place of Work

21

21

American Community Survey Housing Characteristics

• Tenure• Occupancy & Structure• Housing Value• Taxes & Insurance• Utilities• Mortgage/Monthly Rent

22

22

American Community Survey Demographic Characteristics

• Sex• Age• Hispanic Origin• Race

2323

ACS and the Decennial CensusKey Differences

• Residency ACS uses “two-month” rule Decennial census based on concept of “usual

residence”• Employment

Both ACS and Decennial ask respondents if they worked for pay “last week”

ACS collects data year-round and produces an average of the data collected for the period

23

ACS and the Decennial CensusKey Differences (continued)

• Income■ Decennial census income data refer to the

previous calendar year■ ACS asks for income for the previous 12

months• School enrollment

■ Decennial census asks if a person attended school “any time since February 1”

■ ACS asks if a person attended school during the “last 3 months”

2525

American Community SurveyData Releases

• Goal: To produce estimates comparable to the Census 2000 long form data Estimates cover the same small areas (down

to the block group level) as Census 2000 long form, but with smaller sample sizes

• Caveat Smaller sample size = Reduced reliability

25

26

26

American Community Survey Data Releases: Period Estimates

• Period estimates describe the average characteristics over a specific time period

• Point-in-time estimates describe characteristics as of a specific date

• ACS releases 1-year, 3-year, and 5-year estimates for geographic areas that meet specific population thresholds

27

28

28

American Community Survey Methodology

• About 250,000 addresses per month included in sample; 3 million addresses each year

• Group quarters populations included in the ACS since 2006

• Data collected continuously throughout the year by three modes■ Mail■ Phone■ Personal visit

29

American Community Survey Methodology: Caveats

• ACS data are estimates

• ACS data are not counts of the population or housing

• Population counts are produced from the Decennial Census . . . and

■ Counts are updated throughout the decade through the Population Estimates Program

30

American Community Survey Methodology: Sampling error

• The uncertainty associated with an estimate that is based on data gathered from a sample of the population rather than the full population

• Margin of error (MOE) measures the precision of an estimate at a given level of confidence

• MOEs at the 90% confidence level for all published ACS estimates

31

American Community Survey Multiyear Estimates

• Definition A period estimate that encompasses more

than one calendar year• Period for ACS multiyear estimates is either 3 or 5 calendar years■ First release for 3-year estimate was 2008

(for period 2005-2007)■ First release for 5-year estimate is 2010

(for period 2005-2009)

32

American Community Survey Multiyear Estimates: Constructing

• Data are pooled across 36 or 60 months

• Data are weighted to produce estimates

• Estimates are controlled for age, sex, race, and Hispanic origin

• Multiyear estimates are not an average of 1-year estimates

33

American Community Survey Multiyear Estimates: When to Use

• No one-year estimate is available

• Margins of error for 1-year estimates are larger than required

• Analyzing data for small population groups

34

American Community Survey Multiyear Estimates: Currency vs. Reliability

Currency Reliability1-year estimates provide information based on the last year

Larger sample sizes produce estimates that are more statistically reliable

3-year estimates provide information based on the last year and the 2 years before that

3-year estimates are based on 3 times as many sample cases as 1-year estimates

5-year estimates provide information based on the last year and the 4 years before that

5-year estimates are based on 5 times as many sample cases as 1-year estimates

35

American Community Survey Multiyear Estimates: How to Label

• Multiyear estimates do not represent any one year nor the midpoint of a period

• ACS estimates based on data collected from 2006-2008 should not be labeled “2007” or “2008” estimates

• Correct labeling for multiyear estimate: The child poverty rate for the 2006-2008 period was X percent.

36

American Community Survey Multiyear Estimates: Inflation Adjustment

• Dollar-valued data items are inflation adjusted to the most recent year for the period

• Income, rent, home value, and energy costs

• Adjusted using inflation factors based on the Consumer Price Index (CPI)

• Adjustment designed to put the data into dollars with equal purchasing power

37

American Community Survey Multiyear Estimates: Population Controls

• Estimates of housing units and people controlled to the population estimates derived from the Population Estimates Program

• Multiyear estimates controlled to the average of the individual year’s estimates for the period

38

American Community Survey Multiyear Estimates: Geographic Boundaries

• Multiyear estimates are based on geographic boundaries as of January 1 of the last year in the multiyear period

• Boundary Annexation Survey collects boundary changes

• Boundaries of other statistical areas will be updated every decade in conjunction with the decennial census

39

American Community SurveyMaking Comparisons: Across Geographies

• Only compare the same type of estimate 1-year estimates to other 1-year estimates 3-year estimates to other 3-year estimates 5-year estimates to other 5-year estimates

• Use same time period

2006-2008 in County A

2006-2008 in County B

40

American Community SurveyMaking Comparisons: Kentucky counties

Source: U.S. Census Bureau, American Community Survey Handbook for General Audiences

Less than 20,000 people20,000 to 64,999 people65,000 or m ore people

Population, July 2007

Figure 3: Counties in Kentucky by Population Size, 2007

Popula tion , Ju ly 2007

0.00 to 20000 .00

20000 .00 to 65000 .00

65000 .00 to 800000 .00

Fulton

FranklinFayette

41

American Community SurveyMaking Comparisons: Across Geographies

2009 2007-2009 2005-2009

Fayette County X X X

Franklin County X X

Fulton County X

American Community SurveyMaking Comparisons: ACS Questionnaire Changes

42

See: About the ACS > Survey Questionnaire > ACS – Summary of Questionnaire Changes

43

American Community SurveyMaking Comparisons: Which to Compare

1999 to 2001

2000 to 2002

2001 to 2003

2002 to 2004

2003 to 2005

1999 2000 2001 2002 2003 2004 2005

44

American Community Survey Making Comparisons: Different Time Periods

• Same geographic area

■ Use caution if geographic boundaries have changed over time

■ Easier to compare non-overlapping periods

■ Make comparisons using the same length time period

45

American Community SurveyMaking Comparisons: Between Data Sets

• Differences exist between ACS and Census 2000

• Comparisons can be made for most population and housing subjects

• Crosswalk available■ “Compare”■ “Compare with Caution”■ “Do Not Compare” http://www.census.gov/acs/www/UseData/compACS.htm

47

Scroll down page . . .

48

American Community Survey Summary on Multiyear Estimates

• Multiyear estimates are period estimates and should be interpreted / labeled as such

• Data users should consider the tradeoffs of currency versus reliability

• Comparisons between estimates of different geographies should be based on ACS data from the same time periods

• It is easier to compare estimates from non-overlapping periods

49

American Community Survey Tips to Getting the Data You Need

• Broaden geography■ Place level to county level, for instance

• Expand timeframe, if choice is available■ Use 5-year estimate instead of 3-year■ Use 5- or 3-year estimate instead of single

year

• Collapse tables■ Lower margins of error

50

ACS Main Page

51

American Community Survey Tips to Getting the Rural Data You Need: Case Study

52

53

Other Surveys

andPrograms

1

2

1

Scroll down page . . .

2

6060

Thank you!

Seattle Regional Census CenterPartnership & Data Services19820 North Creek Parkway

Bothell, WA 98011

Linda ClarkInformation Services Specialistlinda.clark@census.gov425-908-3060