APT · DATA QUALITY AUDIT · NOTE 13

A cancelled transaction must leave the price baseline

A controlled six-record audit applies MOLIT's official cancellation status before calculating a comparable-price median.

SOURCE SNAPSHOT

Start with provenance before arithmetic.

INPUT AND EVIDENCE LEDGER

Classify every field before using it.

FieldValueOrigin
Reported prices₩780M, ₩800M, ₩820M, ₩830M, ₩840M, ₩1,200MControlled test fixture
Cancelled record₩1,200MOfficial 해제 status applied
Comparable filterSame complex and area bucketAPT rule under test
StatisticMedianRobust baseline choice

REPRODUCIBLE WORK

Run the quality-control chain.

CheckFormula or ruleResult
Unfiltered medianAverage of third and fourth values₩825M
Apply statusExclude the record marked 해제Five active records remain
Active medianMiddle of five active values₩820M
Audit finding₩825M − ₩820M₩5M upward bias in this fixture

DECISION READING

The audit finding.

The bias is small in this fixture but can be material in thin markets. The status filter must happen before summaries, highs, recovery ratios, or rankings are calculated.

OWNER AUTHORIZATION + VERIFICATION RECORD

One accountable operator and a reproducible check record.

The TOOOLBOX site owner authorized this publication scope and remains the correction contact. The checks below were completed during preparation with AI-assisted implementation; they are an audit record, not a claim of licensed professional review.

Review ID
TB-APT-13-20260902
Owner role
TOOOLBOX site owner and developer
Release scope
Owner-authorized · 2026-09-02
Correction channel
Public contact page
  1. Confirmed the disclosure system's cancellation legend.
  2. Ran the fixture with and without the cancelled record.
  3. Checked that no fixture price is described as a live market transaction.

BOUNDARIES

What passed data checks still cannot prove.

  • The six prices are a transparent test fixture, not claims about a named apartment.
  • Cancellation status does not explain why the transaction was cancelled.
  • Other revisions and matching errors require separate checks.

SENSITIVITY

Failure modes to retest.

  • The effect grows when the sample is smaller or the cancelled price is more extreme.
  • Mean prices are usually more sensitive to an outlier than medians.
  • Late cancellation reports require the stored baseline to be recomputed.

MORE APT DECISION NOTES

Compare another evidence pattern.

The related notes deliberately use different questions, data states, and editorial forms.

12 · Use the official rate range as a stress band14 · Normalize area before comparing two sale records