SPB Git

spb/wp29_uqo

Public

# Data audit (P1)

file SHA-256 data rows cols date range missing cpi dup dates
cpi_vintage_2016-07-15.csv 281fbcdd6a6eeb3e9cb7c1f20476e6bd1f7b925bf140606fe46538fe83f2c83e 834 date,cpi 1947-01..2016-06, no gaps 0 0
cpi_vintage_2026-10-28.csv 8220d5b4d70ca32fc2c7b1975651c515967db8a87053cf725159c63ed274cfba 153 date,cpi 2014-01..2026-09, no gaps 1 (2025-10, empty cell) 0
cpi_assembled.csv ff732b201a525d6fb171d4e8b2d470f986863c1547a1928e42bb197c0777d44d 957 date,cpi,vintage 1947-01..2026-10, gap at 2016-07 1 (2025-11) 0
README.md ac136bff13bbdb5afac60e0404212ea1f73f992bd5cca1c1e7a6599df78f8965 — — — — —

SHA-256 of files match bundle.json. (README lists hashes of the raw downloads before reformatting; they differ from the reformatted files, as the README states reformatting occurred.) Units: index 1982-84=100, 3 decimals. All dates first of month, sorted. No month-on-month jump >3% in either vintage.

# Anomalies

  1. Vintage 2026-10-28 has no value for 2025-10 (empty cell; source publishes none). Not imputed: g_2025-10 is missing (only window month affected; g_2026-10 is outside the window).
  2. Vintages overlap 2014-01..2016-06 (30 months); revisions up to 0.455 index points. Rule: use 2026-10-28 values.
  3. cpi_assembled.csv has assembly errors: (a) uses 2016-07-15 values for the overlap 2014-01..2016-06 (labelled vintage 2016-07-15) instead of the latest vintage; (b) month 2016-07 is missing and all 2026-vintage values from 2016-07 onward are shifted one month later (value of 2016-07 labelled 2016-08, ..., 2026-09 value labelled 2026-10; empty 2025-10 shows up as 2025-11). Handling: assembled file read for audit only; not used for any estimate.
  4. g_t for 2014-01..2014-12 combine P_t from vintage 2026 and P_{t-12} from vintage 2016 (different revision states/seasonal factors) — inherent to the rule, documented.

# Availability-rule decisions

Use vintage files only; latest vintage per month; no imputation.

Files · main
Menu

Theme