1 / 8

Utilizing ACS 1-year and 3-year Data

Utilizing ACS 1-year and 3-year Data. Jerry Deichert and David Drozd Nebraska SDC National SDC Meeting, October 2009. Reasons for Using 3-year Data. Expanded geographic coverage Smaller error, especially for subgroups PUMS is three times larger (3 percent compared with 1 percent).

Download Presentation

Utilizing ACS 1-year and 3-year Data

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Utilizing ACS 1-year and 3-year Data Jerry Deichert and David Drozd Nebraska SDC National SDC Meeting, October 2009

  2. Reasons for Using 3-year Data • Expanded geographic coverage • Smaller error, especially for subgroups • PUMS is three times larger (3 percent compared with 1 percent)

  3. Population Size • Nebraska, like many states with large rural populations, has few areas with 65,000+ population Area65,000+20,000-64,999 • Counties 3 16 • Cities 2 11 • Metros 3 3 • Micros 1 10 • School Districts 3 15 • PUMAs 14 14

  4. Comments • Overlapping time periods • Income is for previous 12 months • Initial release of multi-year estimates is of prime importance; afterwards only 1 of 3 years of data changes • Last year’s new 3-year estimates had great interest (first new data since 2000 for many areas), little interest this year • More useful as cross-sectional rather than time series • Numbers are not consistent with most recent population estimates • Small areas may have extreme volatility in economic measures, not reflected in three year period • Small areas still may have large MOEs, especially for subgroups

  5. 3-year Estimates Allow for Analysis of Subgroups with Large MOE: Black Poverty in Omaha Metro YearPercentMOERank* 2005 40.4 4.8 3rd Highest of 87 2006 29.7 5.2 25th Highest of 95 2007 36.7 5.9 6th Highest of 99 2005-07 35.7 3.5 4th Highest of 100 2008 30.3 5.5 18th Highest of 96 * Rank is among the largest 100 metros at that time

  6. Comments • Because of sampling error, there may be large differences in yearly point estimates that influence the 3-year estimate • What is the true level in reality? Which estimate was more likely to be correct – 40% or 30% in poverty • 3-year estimate may mask important changes that are occurring • Numbers can not be used for counts, relying on percentages appears more appropriate

  7. Comparison of Nebraska Net Migration (using ACS B07000 & B07400 series) Variable2007 1-yr2005-07 3-yr Net Movement - 1,754 - 2,581 Male - 235 - 2,652 Female - 1,519 + 71 Hispanic - 2,336 + 752 White, NH +5,324 - 1,888 Under age 18 - 2,063 + 32 Age 40+ - 2,577 - 903 Bachelor’s + - 1,581 - 1,493

  8. Comments • 3-year estimates may be difficult to interpret, what does net migration over the 3-year period mean? • Numbers are not consistent with most recent population estimate methodology • Changes to the methods to define net international inmigration could have impacted especially the Hispanic/Latino figures

More Related