test_scores_county_year
Stanford SEDA v6 standardized learning rate scores by county, year, and subject (mth/rla). Scores are z-scores relative to national mean (0 = national average). Covers grades 3-8; most recent year 2019.
tier bregression_model
overview
overview
~3,150 counties x ~9 years. SEDA covers ~98% of US public school districts; small-district suppression cascades to county.
current vintage — SEDA v4.1 (2009-2018 testing years)
history — SEDA: 2009 to present (latest release 2018)
provenance
source & licensing
authority
Stanford Education Data Archive
dataset
Stanford Education Data Archive (SEDA) - district-level test scores
source url
license
Creative Commons Attribution 4.0
citation
Reardon, S.F., Ho, A.D., Shear, B.R., Fahle, E.M., Kalogrides, D., Jang, H., & Chavez, B. (2021). Stanford Education Data Archive (Version 4.1).
schema
fields
| name | type | definition |
|---|---|---|
| country_id | string | ISO alpha-2 country code (always 'US' for domestic tables). |
| county_idkey | string | 5-character FIPS code identifying the county.Joins dim.counties on county_id. |
| county_name | string | Human-readable county name corresponding to county_id. |
| flag_estasmt | int64 | Integer flag indicating whether assessment counts or scores are estimated or suppressed, typically due to small cell sizes or data quality conditions. Non-zero values signal that the row's statistics should be interpreted with caution. |
| gap_white_black | float64 · scale score | Racial achievement gap computed as mean_score_white minus mean_score_black. Positive values indicate White students outperform Black students; larger magnitudes reflect wider disparities. |
| gap_white_hispanic | float64 · scale score | Racial achievement gap computed as mean_score_white minus mean_score_hispanic. Positive values indicate White students outperform Hispanic students; larger magnitudes reflect wider disparities. |
| grades_included | int64 · count | Number of grade levels whose assessment results are aggregated into the row's statistics. Higher values indicate broader grade coverage. |
| mean_score_all | float64 · scale score | Average standardized test scale score across all students in the county for the given subject and year. Higher values indicate stronger academic performance. |
| mean_score_asian | float64 · scale score | Average standardized test scale score for Asian students in the county. Higher values indicate stronger academic performance for this subgroup. |
| mean_score_black | float64 · scale score | Average standardized test scale score for Black students in the county. Higher values indicate stronger academic performance for this subgroup. |
| mean_score_econ_disadvantaged | float64 · scale score | Average standardized test scale score for economically disadvantaged students (typically those qualifying for free or reduced-price lunch) in the county. Higher values indicate stronger performance for this subgroup. |
| mean_score_hispanic | float64 · scale score | Average standardized test scale score for Hispanic students in the county. Higher values indicate stronger academic performance for this subgroup. |
| mean_score_non_econ_disadvantaged | float64 · scale score | Average standardized test scale score for students who are not economically disadvantaged in the county. Higher values indicate stronger performance for this subgroup. |
| mean_score_white | float64 · scale score | Average standardized test scale score for White students in the county. Higher values indicate stronger academic performance for this subgroup. |
| state_id | string | 2-character FIPS code identifying the state.Joins dim.states on state_id. |
| subject | string | Academic subject assessed, such as math or reading/ELA. Identifies which tested domain the row's score statistics apply to. |
| tot_assessments | int64 · count | Total number of individual student assessments included in the county's score statistics for the given subject, year, and grade range. |
| yearkey | int64 | Reference year of the observation. |
relationships
joins
primary key
county_id, year
common joins
dim.geographies on county_id
districts_lea via county aggregation
enrollment_district_year on (leaid, year)
usage
how to use this table
method
SEDA equates state assessments to a common scale using NAEP linking, producing comparable test scores across states. District means rolled to county weighted by enrollment.
do not use for
Post-pandemic (latest year is 2018 - pre-COVID); causal inference (descriptive); sub-district school comparisons.
known issues
Latest year is 2018 - does not reflect pandemic learning loss. State assessment changes affect linking.
last updated · May 5, 2026