1# F1-conf-01 — 12-month CPI inflation from two data vintages23## Question412-month growth rate g_t = 100·(P_t/P_{t−12} − 1) of CPIAUCSL (SA) for each month 2001-01 … 2026-09, with P taken from the most recent vintage covering the month, and summaries thereof.56## Data and exclusions7- `cpi_vintage_2016-07-15.csv` (834 rows, 1947-01…2016-06) and `cpi_vintage_2026-10-28.csv` (153 rows, 2014-01…2026-09) — authoritative inputs (`n_input_rows`).8- `cpi_assembled.csv` (957 rows) was read **only for auditing**. It contains assembly errors: 2014-01…2016-06 taken from the old vintage, 2016-07 missing, and all later values shifted one month later (so it runs to a non-existent 2026-10). It was not used for any computation (`data_issues`).9- The 2026-10-28 vintage has no value for 2025-10 (source reports none). Not imputed, so g for 2025-10 is missing (`missing_growth_months`, `n_months_missing_growth` = 1). (g for 2026-10 would also be affected but lies outside the window.)10- The vintages overlap for 2014-01…2016-06 and differ in all 30 months (revisions, max 0.455 index points); the 2026 vintage is used there (`data_issues`).11- Exclusion ledger (`out/exclusions.csv`): 957 monthly levels 1947-01…2026-09 → 309 window months → 308 months with computable g_t (`n_analysed`).1213## Method14Combined series: 2026-10-28 vintage for 2014-01…2026-09, 2016-07-15 vintage before. g_t computed by 12-month lag on that series, no interpolation. Summaries are simple arithmetic means over computable months. Deterministic, no randomness (`random_seed` = null). Code: `out/analysis.py`.1516## Results17- Window coverage: first growth month 2001-01 (`first_growth_month`), last month with a level 2026-09 (`last_month`); 308 computable months (`n_months_growth`), 1 missing (`n_months_missing_growth`).18- Mean 12-month growth over the window: 2.574% (`mean_growth_12m`).19- Baseline sub-period 2001-01…2013-12: 2.361% (`mean_growth_12m_2001_2013`, 156 months, `n_growth_2001_2013`); 2014-01…2026-09: 2.793% (`mean_growth_12m_2014_2026`, 152 months, `n_growth_2014_2026`).20- Named months: 2014-06 2.098% (`growth_2014_06`); 2016-07 0.868% (`growth_2016_07`); 2020-05 0.198% (`growth_2020_05`); 2022-06 8.979% (`growth_2022_06`); 2026-09 3.717% (`growth_2026_09`).21- Maximum 8.979% in 2022-06 (`max_growth_12m`, `max_growth_month`); minimum −1.959% in 2009-07 (`min_growth_12m`, `min_growth_month`).22- Feasibility: "partial" (`feasibility`, `feasibility_reason`) because one window month lacks g_t.2324## Uncertainty25The estimands are deterministic transformations of published index levels; there is no sampling uncertainty model and no confidence intervals are reported. Dispersion of g_t over the window: SD 1.741 pp (`sd_growth_12m`). The main source of "uncertainty" is data revision: values depend on the vintage (the overlap months differ by up to 0.455 index points between vintages, `data_issues`).2627## Limitations and open issues28- g_t for 2014-01…2014-12 mixes a 2026-vintage numerator with a 2016-vintage base (the 2026 extract starts at 2014-01), as the availability rule prescribes; this mixes seasonal-factor vintages.29- 2025-10 g_t is missing; window means cover 308 of 309 months, the 2014–2026 mean covers 152 of 153 months.30- README SHA-256 values refer to raw downloads before reformatting and could not be verified against the provided files.31