assembly-economics/simulations/gadm02/results/matching.md

GADM-0.4: model matching on observed series

Generated by simulations/gadm02/matching.py (ASSEMBLY-WP-0012). Method: research/ModelMatching.md. Data: observed_series.json. Weights are likelihood (AIC) weights over the eight candidates; all candidates fit the same two values (t0, s). Each score adds the calibrated K_Ω level range at the end of the window. Sentiment is not scored yet (data precede checkpoint 0).

US

Series: U.S. Census Bureau BTOS Q7 (National.xlsx), periods 2025-24 to 2026-20 (biweekly)

Candidate	log-likelihood	weight	t0	K_Ω at window end
B3/loop off	-8.3	0.230	1.20	0.172
B2/loop off	-8.5	0.195	0.20	0.077
B2/loop on	-8.5	0.187	0.20	0.077
B3/loop on	-8.6	0.174	1.15	0.167
B4/loop on	-9.0	0.122	1.65	0.244
B4/loop off	-9.2	0.092	1.90	0.278
B1/loop off	-80.7	0.000	0.00	0.054
B1/loop on	-80.8	0.000	0.00	0.054

Best: B3/loop off (weight 0.23). Anchor weights: B1 0.00, B2 0.38, B3 0.40, B4 0.21. Loop weights: off 0.52, on 0.48.

EU

Series: Eurostat isoc_eb_ai, EU27_2020, reference years 2023-2025 (2021: 7.65, before generative AI, excluded)

Candidate	log-likelihood	weight	t0	K_Ω at window end
B3/loop on	-2.3	0.484	0.45	0.196
B3/loop off	-2.3	0.452	0.50	0.201
B2/loop off	-5.0	0.031	0.00	0.099
B2/loop on	-5.1	0.028	0.00	0.099
B4/loop on	-7.1	0.004	0.95	0.302
B4/loop off	-8.1	0.001	1.00	0.316
B1/loop off	-56.7	0.000	0.00	0.058
B1/loop on	-56.7	0.000	0.00	0.058

Best: B3/loop on (weight 0.48). Anchor weights: B1 0.00, B2 0.06, B3 0.94, B4 0.01. Loop weights: off 0.48, on 0.52.

DE

Series: Eurostat isoc_eb_ai, DE, reference years 2023-2025 (2021: 10.56, excluded)

Candidate	log-likelihood	weight	t0	K_Ω at window end
B2/loop off	-1.1	0.277	0.00	0.102
B2/loop on	-1.2	0.267	0.00	0.102
B3/loop on	-1.2	0.249	0.65	0.215
B3/loop off	-1.4	0.205	0.70	0.221
B4/loop on	-7.1	0.001	1.25	0.352
B4/loop off	-9.3	0.000	1.40	0.385
B1/loop off	-42.3	0.000	0.00	0.060
B1/loop on	-42.3	0.000	0.00	0.060

Best: B2/loop off (weight 0.28). Anchor weights: B1 0.00, B2 0.54, B3 0.45, B4 0.00. Loop weights: off 0.48, on 0.52.

US: IMM regime filter on the observed series (WP-0017-T05)

Calendar t 0 = 2025-08-01. Indicators: adoption (BTOS, biweekly), investment (L5b, Census private office construction incl. data centers, monthly), discovery channel (StatCounter search share, monthly). Observations after the start: {'adopt': 22, 'invest': 5, 'pd': 10}. Start: static matching weights; quarterly IMM steps from t 0.32 to 1.17. Flips judged on anchor weights.

Calendar t	B1	B2	B3	B4	loop off	loop on
0.32	0.00	0.38	0.40	0.21	0.52	0.48
0.57	0.00	0.00	1.00	0.00	0.70	0.30
0.82	0.00	0.00	1.00	0.00	0.77	0.23
1.07	0.00	0.00	0.00	1.00	0.49	0.51

Robustness of the last evaluation (anchor weights):

Variant	B1	B2	B3	B4
noise × 2	0.00	0.00	0.04	0.96
noise × 3	0.00	0.00	0.58	0.42
without investment	0.00	0.00	0.31	0.69

Last evaluation (US): anchor B4 with weight 1.00; previous quarter B3 1.00. A flip needs the new anchor at ≥ 0.75 in two consecutive quarters; a change seen in one quarter is a flip candidate to check at the next review. Confirmed flips: none.

US: IMM filter with observation noise calibrated from residuals (WP-0015-T07)

Residual standard deviations around the best static regime (B3/loop off), model error included:

Indicator	assumed noise	residual sd	used
adopt	0.03	0.0258	0.0300
invest	0.05	0.0784	0.0784
pd	0.01	0.0086	0.0100

Calendar t	B1	B2	B3	B4
0.32	0.00	0.38	0.40	0.21
0.57	0.00	0.00	1.00	0.00
0.82	0.00	0.00	1.00	0.00
1.07	0.00	0.00	0.00	1.00

Last quarter: B4 1.00. Confirmed flips: none.