Education Data Source Meps

MEPS Data Source Reference

Model Estimates of Poverty in Schools (MEPS) — Urban Institute modeled estimates of school-level poverty (% students at or below 100% FPL), derived from CCD and Census SAIPE data (public schools, 2009-2022, 2-3 year lag). Use when analyzing school poverty rates, comparing poverty across states, or when FRPL data is unreliable due to CEP enrollment. Unlike FRPL, MEPS provides consistent cross-state measurement at a standardized 100% FPL threshold. Public schools only.

School-level poverty measure from the Urban Institute that is comparable across states and time, unlike Free/Reduced-Price Lunch (FRPL) data.

CRITICAL: Value Encoding

The Education Data Portal returns MEPS data with integer-encoded categorical and identifier columns. This differs from some external documentation:

Column	Portal Type	Example Value	Notes
fips	Int64	6	State FIPS as integer (California = 6)
ncessch	Int64	10000200277	12-digit NCES school ID as integer
leaid	Int64	100002	7-digit district ID as integer
gleaid	Int64	100013	Geographic LEA ID as integer
year	Int64	2018	Academic year (fall semester)

Missing values: Unlike CCD, MEPS uses native nulls rather than negative coded values (-1, -2, -3). While the codebook lists these codes, actual Portal data contains nulls for missing values.

See ./references/variable-definitions.md for complete encoding tables.

What is MEPS?

MEPS is a modeled estimate of the share of students from households with incomes at or below 100% of the Federal Poverty Level (FPL).

• Purpose: Provide consistent school poverty measurement across all US states
• Key advantage: Comparable across states (unlike FRPL which varies by state policy)
• Data level: School-level (individual schools)
• Coverage: 2009-2022 (actual Portal data range)
• Source: Urban Institute, derived from CCD and SAIPE data
• Primary identifier: ncessch (12-digit NCES school ID)
• Public schools only: Does not cover private schools

Reference File Structure

Decision Trees

Should I use MEPS or FRPL?

What is your research goal?
├─ Compare poverty across states → Use MEPS
│   └─ FRPL varies by state policy, MEPS is standardized
├─ Track poverty over time (post-2010) → Use MEPS
│   └─ CEP adoption makes FRPL inconsistent
├─ Study CEP/universal meals impact → Use both
│   └─ Compare MEPS (true poverty) vs FRPL (program participation)
├─ Match historical research (pre-2010) → Consider FRPL
│   └─ MEPS only available 2006+, but FRPL was more reliable then
├─ Need 185% FPL threshold → Use FRPL with caveats
│   └─ MEPS only measures 100% FPL
└─ Federal funding formulas → Check formula requirements
    └─ Some formulas mandate FRPL; note limitations

Which MEPS variable should I use?

Which estimate type?
├─ Standard analysis → `meps_poverty_pct`
│   └─ Original modeled estimate
├─ High-poverty district adjustment → `meps_mod_poverty_pct`
│   └─ Modified MEPS for districts where model underestimates
├─ Need confidence bounds → `meps_poverty_se`
│   └─ Standard error for uncertainty analysis
└─ Categorical analysis → Derive from `meps_poverty_pct`
    └─ Create quartiles/quintiles as needed

How do I access MEPS data?

Access method?
├─ Mirror download (recommended) → See "Data Access" section below
└─ Join with other data → Use `ncessch` as join key

Quick Reference: MEPS Variables

Data Access: MEPS data is fetched from mirrors (parquet/CSV). See datasets-reference.md for canonical paths, mirrors.yaml for mirror configuration, and fetch-patterns.md for fetch code patterns.

Portal Field Names

The Portal field names differ from some external MEPS documentation:

Variable Reference

All ID and categorical columns use integer encoding in Portal data:

Key Identifiers

Missing Data Codes

Important: Unlike CCD and most other Portal sources, MEPS does not use -1, -2, -3 coded values. Use null checks:

# Correct
valid_data = df.filter(pl.col("meps_poverty_pct").is_not_null())

# Wrong (MEPS doesn't use -1, -2, -3 coded values)
# df.filter(pl.col("meps_poverty_pct") >= 0)  # Unnecessary

Data Access

Datasets for MEPS are available via the mirror system. See datasets-reference.md for canonical paths, mirrors.yaml for mirror configuration, and fetch-patterns.md for fetch code patterns.

Codebooks are .xls files co-located with data in all mirrors. Use get_codebook_url() from fetch-patterns.md to construct download URLs:

url = get_codebook_url("meps/codebook_schools_meps")

Truth Hierarchy: When interpreting variable values, apply this priority:

1. Actual data file (what you observe in the parquet/CSV) -- this IS the truth
2. Live codebook (.xls in mirror) -- authoritative documentation, may lag
3. This skill documentation -- convenient summary, may drift from codebook

If this documentation contradicts the codebook, trust the codebook. If the codebook contradicts observed data, trust the data and investigate.

Filtering

# Filter to valid poverty estimates only (drop nulls)
df = df.filter(pl.col("meps_poverty_pct").is_not_null())

# High-poverty schools (top quartile nationally)
high_poverty = df.filter(pl.col("meps_poverty_ptl") >= 75)

# Use modified MEPS for high-poverty districts
df = df.with_columns(
    pl.when(pl.col("meps_mod_poverty_pct").is_not_null())
    .then(pl.col("meps_mod_poverty_pct"))
    .otherwise(pl.col("meps_poverty_pct"))
    .alias("poverty_pct_best")
)

Common Pitfalls

Why MEPS Instead of FRPL?

Critical insight: As of 2020, ~60% of schools participate in CEP or other universal meal programs, making FRPL increasingly unreliable as a poverty proxy.

Key Methodological Points

1. Model-based: MEPS uses a linear probability model, not direct counts
2. Calibrated to SAIPE: District totals align with Census poverty estimates
3. School-specific: Reflects enrolled students, not neighborhood demographics
4. 100% FPL threshold: Lower than FRPL (185%) - captures deeper poverty
5. Public schools only: Does not cover private schools

Common Use Cases

Joining MEPS with Other Data

Limitations

• Years available: 2009-2022 (actual Portal data range)
• Public schools only: No private school coverage
• Modeled estimates: Subject to estimation error (use meps_poverty_se)
• 100% FPL only: Does not capture near-poverty (100-185% FPL)
• Not real-time: 2-3 year data lag typical

Related Data Sources

Topic Index