NAEP Technical DocumentationPrimary Sampling Unit Generation: Non-Metropolitan Statistical Areas for the 2012 Assessment

A software algorithm was utilized to define a preliminary set of primary sampling units (PSUs) satisfying the design constraints. The input set consisted of all of the non-metropolitan counties. The software formed PSUs that satisfied the minimum size constraints while not crossing state boundaries. The software also minimized the maximum point-to-point distance for the candidate PSUs, while still satisfying the minimum size constraints (15,000 youths in the Northeast and South Census regions, and 10,000 youths in the Midwest and West Census regions). 'Worst first' was the general approach: the county which had the PSU with the largest maximum point-to-point distance was fitted first, with those counties that best fit within a PSU containing the 'worst-first' county put together to form the first PSU. The algorithm was then run on the remaining counties not yet assigned to a PSU finding the next 'worst-first' county.

Initially, there were 22 counties that could not be combined into PSUs to satisfy the minimum size constraints while still remaining within a single state. Nine of the PSUs (formed from 12 of these counties) that were below the minimum size requirement were allowed to stand, since satisfying the minimum size requirement was not reasonably possible. The remaining counties were in Alaska, for which PSUs were manually drawn to better respect interstate highways (being drawn along the axis of these highways) and mountain ranges (avoiding crossing of ranges with poor road access). For Alaska, the proto-PSUs created by the program were replaced by the PSUs created for the NAEP 2004 assessment. The end result of this procedure was that all non-metropolitan PSUs were contained within state boundaries. There were a total of 670 final non-metropolitan PSUs.

The table below presents the number of PSUs, the number of counties represented, and the estimated number of youths (total and mean per PSU) by Census region. The estimated number of youths (persons age 0 to 17) for each county comes from the 2009 U.S. Census Bureau's Population Estimates Program.

Non-Metropolitan Statistical Area primary sampling unit (PSU) frame, by census region: 2012
Census region	PSUs	Counties	Youths	Mean number of youths per PSU
NOTE: The U.S. Census Bureau's Population Estimates Program (http://www.Census.gov/popest/) yearly publishes total resident population estimates by demographics such as age, sex, race, and Hispanic origin for the nation, states, and counties. SOURCE: U.S. Department of Education, Institute of Education Sciences, National Center for Education Statistics, National Assessment of Educational Progress (NAEP), 2012.
Total	670	2,052	11,661,755	17,406
Northeast	50	94	1,111,662	22,233
Midwest	249	769	3,561,130	14,302
South	269	872	5,263,030	19,565
West	102	317	1,725,933	16,921

Last updated 26 February 2016 (GF)

Printer-friendly Version