Table of Contents  |  Search Technical Documentation  |  References

NAEP Assessment Sample Design → NAEP 2006 Sample Design → Selection of Primary Sampling Units (PSUs) for the 2006 Assessment → Primary Sampling Unit (PSU) Generation: Metropolitan Statistical Areas for the 2006 Assessment

Primary Sampling Unit (PSU) Generation: Metropolitan Statistical Areas for the 2006 Assessment

The 2004 definitions of Core Based Statistical Areas (CBSAs) and Combined Statistical Areas (CSAs), which are also referred to as Metropolitan Statistical Areas (MSAs), were used to define primary sampling units (PSUs). These definitions were the most recently available definitions from the U.S. Office of Management and Budget (OMB) at the time of the 2006 PSU frame creation. The new CBSA areas consisted of clusters of one or more counties classified as metropolitan and micropolitan statistical areas.

The metropolitan PSUs were manually created by grouping counties in MSA areas. Each MSA constituted a PSU, except for those areas that crossed state boundaries. These areas were split into "proto-PSUs" along state boundaries. Proto-PSUs consisted of portions of MSAs within individual states.1 For example, the New York-Newark-Bridgeport, NY-NJ-CT-PA was partitioned into four proto-PSUs by state.  

If the proto-PSU did not violate the size constraints, it was defined as a PSU. In some cases, these proto-PSUs violated the minimum size constraint of 15,000 youths for the Northeast or South Census regions, and 10,000 youths for the Midwest and West Census regions. There were 14 of these proto-PSUs violating size constraints. In one of these 14 cases where the size was close to the constraint, it was defined as a PSU. In the remaining 13 smaller cases, these proto-PSUs were combined with the adjacent MSA proto-PSUs to form the final PSUs. In these cases, the combined PSUs crossed state boundaries.

A total of 29 of the newly-created PSUs were defined as certainty PSUs. The remaining 370 PSUs comprised the MSA frame for PSU sampling, covering a total of 888 counties. The table below presents estimates for the number of youths by Census region (these estimates come from the county-level estimates of numbers of persons aged 0 to 17 from the 2003 U.S. Census Bureau's Population Estimates Program;2 these estimates were the most recent demographic data at the time of the PSU selection).

Noncertainty Metropolitan Statistical Area (MSA) primary sampling unit (PSU) frame, by Census region: 2006
Census region PSUs Counties Youths
Total 370 888 31,194,309
Northeast 46 83 4,708,570
Midwest 100 246 7,407,285
South 153 458 12,638,746
West 71 101 6,439,708
SOURCE: U.S. Department of Education, Institute of Education Sciences, National Center for Education Statistics, National Assessment of Educational Progress (NAEP), 2006.

1  Note that this is a change from earlier NAEP cycles. Field personnel had indicated that contacts with state officials were very important in the process of recruiting schools. Because of this, it was decided that making single-state rather than multi-state PSUs was a better approach. In a few cases, small-size proto-PSUs were combined across state lines, if it was necessary to satisfy other criteria.

2  The U.S. Census Bureau's Population Estimates Program ( yearly publishes total resident population estimates by demographics such as age, sex, race, and Hispanic origin for the nation, states, and counties.

Last updated 13 April 2010 (GF)

Printer-friendly Version