Aggregate service coverage differences

Method, inputs and limits

Reports disclosed aggregate group coverage and differences, suppresses small cells and prevents overlapping group totals. Method version 0.2.0. Explain a disparity, infer discrimination, predict individual outcomes or collect individual records.

Visible mathematics / decision rules

coverage = served / eligible × 100%, when eligible > 0

observed coverage gap = largest disclosed coverage − smallest disclosed coverage

budget burden share = disclosed group budget burden / total disclosed burden × 100%, only for disjoint, unsuppressed, complete burden data

sum only verified disjoint group counts; suppress totals when any small cell is suppressed

What this result cannot establish

• Bounded implementation from supplied acceptance checks and restored CORE definitions; scope choices are explicit below.
• Coverage differences are descriptive; no causal explanation, discrimination finding or policy ranking follows.
• Budget burdens are optional, nonnegative integer minor currency units with explicit currency, price basis and reference year; unknown burdens are not treated as zero.
• Suppression applies to eligible, served and complementary unserved cells below the supplied threshold. Suppressed counts, rates and aggregate totals are withheld.
• Duplicate group labels or declared overlap prevent summation. Disjointness is supplied, not inferred from labels.
• Supply a period and common eligibility definition for every group to check comparability. Mismatches or partial metadata withhold cross-group metrics.
• A manual aggregate table gives the same result. Only aggregate counts are accepted by this schema.

What would falsify the assumptions?

• The result fails if eligibility, counting periods, group boundaries or overlap declarations differ.
• Independent aggregate administrative audits can contradict the group counts.
• For each group served ≤ eligible; totals are shown only with declared disjointness and no suppression.
• Recompute the same disclosed aggregate ratios manually.
• This is descriptive arithmetic, never a causal estimate of equitable treatment.
• MAR adds no benefit if a manual aggregate review is equally accurate; disclosure of small cells would demonstrate added privacy risk.
• Assumptions fail if the supplied definitions, units, period, scope or source records are wrong or incomplete.
• An independent source audit or replication may contradict an input or the recorded dependency.
• This method creates no resources. Physical conservation is checked in the inventory and transfer ledgers; descriptive graphs and checklists are not resource-flow models.
• The same equations and review checklist can be reproduced with a spreadsheet or structured human-only process.
• This is deterministic arithmetic, a descriptive comparison or a structured governance check, not a fitted causal effect or forecast. Fictional inputs remain an exercise.
• Equal or worse measured errors, net review effort, disclosure burden or fallback under MAR would show no added benefit or added risk; no improvement is assumed.

{
  "observations": {
    "unit": "requests",
    "origin": "synthetic",
    "sources": [
      {
        "id": "SYN-001",
        "kind": "synthetic",
        "label": "Fictional demonstration E; two disjoint counties",
        "url": null
      }
    ],
    "burdenCurrency": "USD",
    "burdenPriceBasis": "nominal",
    "burdenBaseYear": 2026,
    "groups": [
      {
        "id": "A",
        "label": "County A",
        "unit": "requests",
        "eligible": 100,
        "served": 70,
        "budgetBurdenMinor": null,
        "overlapWith": []
      },
      {
        "id": "B",
        "label": "County B",
        "unit": "requests",
        "eligible": 100,
        "served": 90,
        "budgetBurdenMinor": null,
        "overlapWith": []
      }
    ]
  },
  "parameters": {
    "groupRelationship": "disjoint",
    "smallCellThreshold": 10
  }
}

{
  "totalEligible": 200,
  "totalServed": 160,
  "totalCoverage": 80,
  "coverageGap": 20
}

Authoritative background references

• U.S. Census Bureau: Data API developer guidance — Keep dataset year, geography, margins of error, and privacy limits visible. Reviewed 2026-11-09. Reference, not endorsement or validation.

These sources inform definitions or review practices. They do not validate this implementation or endorse MAR.