NAEP Technical DocumentationStratification Variables for the 2017 State Assessment

			Stratification by Urbanicity Classification Stratification by Race/ethnicity Classification Stratification by Achievement Data and Median Income Missing Stratification Variables

The implicit stratification of public schools for the NAEP 2017 state assessments involved four dimensions:

• urbanicity classification (urban-centric locale);
• race/ethnicity classification;
• achievement data or median income; and
• magnet school indicator.
  

The urbanicity stratum is the top-level implicit stratification variable and is assigned within each explicit stratum. It is derived from the NCES urban-centric locale variable and classifies schools based on location (city, suburb, town, rural) and proximity to urbanized areas. It has 12 possible values.

The race/ethnicity stratum classifies schools by the relative magnitude of enrollment of non-Hispanic White, non-Hispanic Black, Hispanic, Asian, American Indian/Alaska Native, Hawaiian/Pacific Islander, and students classified as two or more races represented in schools. The source of the race/ethnicity data is the Common Core of Data (CCD). The race/ethnicity stratum is the second-level variable in the stratification hierarchy and is nested within the urbanicity stratum.

The next stratification dimension is a classification of schools based on either achievement data or median household income. For most states, it is based on achievement data. However, not all states provide achievement data. In these cases, median household income is used instead. Median income comes from the 2010-2014 American Community Survey (ACS), and it corresponds to the zip code area where the school is located.

The final stratification dimension indicates whether a school is classified as a magnet school or not, according to the CCD.  It is used to provide an additional level of classification among the highest achieving schools, to differentiate between high achieving magnet schools and high achieving non-magnet schools. Many domains do not classify any schools as magnet, in which case this variable has no effect on the implicit stratification.    

Missing values for stratification variables were imputed.

The implicit stratification in this hierarchical procedure was achieved via a "serpentine sort" within a given explicit stratum. This sort was accomplished by alternating between ascending and descending sort order on each variable successively through the sort hierarchy. Within this sorted list the schools were arranged in serpentine order by magnet school status and achievement data (or median household income), within each cell determined by the two higher stratification variables (urbanicity and race/ethnicity classifications). Schools were sorted in ascending order for magnet school status and descending order for achievement data/median household income used in every other cell, and in descending order for magnet school status and ascending order for achievement data/median household income used in the remaining cells, giving an ascending-descending-ascending-descending pattern. Schools in these urbanicity and race/ethnicity classification cells were also sorted in serpentine order. Within each urbanicity and race/ethnicity classification cell, schools were sorted in ascending order within one urbanicity stratum, by descending order within the next urbanicity stratum, and so on. The following table shows an oversimplified example to illustrate the ascending-descending-ascending-descending pattern of the serpentine sort. Since the magnet school indicator was not applicable in most domains, it is omitted from the example table for simplicity.

Stratification variables sorted by serpentine sort: 2017

TUDA	Urbanicity	Race/ethnicity level	Achievement score
SOURCE: U.S. Department of Education, Institute of Education Sciences, National Center for Education Statistics, National Assessment of Educational Progress (NAEP), 2017 State Assessment.
Yes	Large City	High minority	20
			22
			27
			30
		Low minority	29
			26
			20
			18
	Mid-size City	Low minority	15
			25
			27
			31
		High minority	35
			32
			30
			28
No	Mid-size City	High minority	20
			22
			27
			30
		Low minority	29
			26
			20
			18
	Large City	Low minority	15
			25
			27
			31
		High minority	35
			32
			30
			28

 

Printer-friendly Version