Presentation is loading. Please wait.

Presentation is loading. Please wait.

Prepared by the North Dakota State Data Center July 20081 Using the American Community Survey for Rural Research Dr. Richard Rathge Professor and Director.

Similar presentations


Presentation on theme: "Prepared by the North Dakota State Data Center July 20081 Using the American Community Survey for Rural Research Dr. Richard Rathge Professor and Director."— Presentation transcript:

1 Prepared by the North Dakota State Data Center July 20081 Using the American Community Survey for Rural Research Dr. Richard Rathge Professor and Director North Dakota State Data Center Rural Sociological Society Annual Meeting Manchester, NH July 31, 2008

2 Presentation Objectives: 1. Highlight some key challenges of using ACS for rural research 2. Illustrate the need for a conceptual shift in the way we approach rural research when using ACS data 3. Initiate dialogue of implications for research and policy

3 Key Challenges for rural areas  Effects of longer period estimates  Consequences of smaller sample size  Rule changes and their impact on trend analyses

4 Period Estimates … ACS vs. Census  Census (conceptually point in time April 1 st )  ACS accumulates 12 months (1-year estimate) 36 months (3-year estimate) 60 months (5-year estimate)  Think of shutter speed on camera

5

6 Rural Statistical Areas Joint Project

7 Nebraska ACS Data  Thanks to Jerry Deichert for data  Omaha city was an ACS test sites: 1997-2004 Can examine 1, 3, 5-year data

8

9

10

11

12

13 Key Challenges for rural areas  Effects of longer period estimates  Consequences of smaller sample size  Rule changes and their impact on trend analyses

14 ACS sample size is smaller than Census  One-year sample is 2.5 % of HHs vs 16.7% for Census long form Over five-year period, ACS sample size is 12.5 percent  Therefore ACS sampling error will be larger

15 Cass County, North Dakota (population 132,585)

16 Grand Forks County, North Dakota

17 People Moving to North Dakota Within the Past Year by State of Origin: 2006 ACS

18 Comparison of 1-year, 3-year, and 5-year Estimates of the Percentage of Persons in Poverty for Omaha, NE: 1999-2005 ACS 1999200020012002200320042005 Single-year estimate 11.412.011.012.313.513.915.3 Single-year MOE 0.81.0 1.51.61.5 Three-year estimate 11.411.712.113.214.2 Three-year MOE 0.50.70.8 Five-year estimate 11.912.513.2 Five-year MOE0.5 0.6

19 Suppression Issues  ACS using suppression similar to the 1970 and 1980 decennial census  Applied to base tables in 1 and 3- year data  Use “data release rules” to protect user from tables “whose reliability is unacceptable”  Suppresses entire table not just unreliable cells

20 41 cells which will cause suppression for smaller counties

21 Key Challenges for rural areas  Effects of longer period estimates  Consequences of smaller sample size  Rule changes and their impact on trend analyses

22 ACS income not compatible with decennial census data  Decennial census asks income in previous calendar year  ACS asks income in previous 12 months Both are inflation adjusted However, Bureau test results show decennial income consistently lower than ACS (4.4% nationwide)  Bureau suggests users “exercise caution”

23 Residency rules very different  Decennial census- “usual place of residence “using 6+ month” rule.  ACS – current residence during the last 2-months. Attempting to better count seasonal residents

24 Once, Only Once, And In The Right Place Residence rules panel charged “to examine census residence rule issues and make recommendations for research and testing to develop the most important residence rules for the 2010 census.”

25 Observations from ACS Question 25 (seasonal housing) testing  Preliminary assessment is that seasonal housing units do not appear to be an issue for areas receiving 1-year estimates  Seasonal housing units are expected to cluster at smaller geographic levels Remarks from Susan Schechter and Deborah Griffin, ACS Office Staff

26 1999-2001 Wisconsin test counties Michael Starsinic, Census Bureau

27 What lessons have we learned thus far?  Need to be more mindful of our data users  Rethink how we interpret and disseminate data to the public  Examine ways in which we can better educate ourselves and data user

28 The Message and the Media: The 2005 ACS Rollout  We reviewed 57 articles in 44 newspapers around the nation that appeared August 15-16 First availability of estimates for all areas greater than 65,000 population  Not just the NY Times and Washington Post; other major metros (Seattle Post-Intelligencer, Houston Chronicle) and smaller papers (Toledo Blade, Lexington Herald-Leader, Anchorage Daily News...) Research from the Committee on National Statistics, National Research Council

29 Key Interest: Change Over Time  Three-fourths of articles featured estimates of change from 2000 to 2005, mostly using the long-form sample for 2000  But only 2 articles expressed caution about comparing the long-form sample and the ACS Research from the Committee on National Statistics, National Research Council

30 Census Bureau Resources  ACS website on Census Homepage  Technical documents/user guides being produced by Census Bureau  State Data Center websites

31

32 Census Bureau’s comparison matrix

33 Demographic Presentation 2008  Dr. Richard Rathge, Director North Dakota State Data Center, Fargo, ND NDSU, IACC 424, Fargo, ND 58105 Richard.Rathge@ndsu.edu Phone: (701) 231-8621 Fax: (701) 231-9730 URL: www.ndsu.edu/sdc


Download ppt "Prepared by the North Dakota State Data Center July 20081 Using the American Community Survey for Rural Research Dr. Richard Rathge Professor and Director."

Similar presentations


Ads by Google