[
 {
  "id": "C1",
  "text": "The pre-specified ARIMA(2,1,0) model does not improve on the naive no-change forecast at h=1: its RMSE is about 2.3% higher.",
  "results_keys": [
   "rmse_model_h1",
   "rmse_naive_h1",
   "rel_improvement_rmse_h1",
   "mae_model_h1",
   "mae_naive_h1"
  ],
  "status": "supported",
  "caveat": "35 evaluated pairs; final-vintage data; only one model specification."
 },
 {
  "id": "C2",
  "text": "At h=3 the ARIMA(2,1,0) model is also slightly worse than naive: RMSE about 0.5% higher and MAE also higher.",
  "results_keys": [
   "rmse_model_h3",
   "rmse_naive_h3",
   "rel_improvement_rmse_h3",
   "mae_model_h3",
   "mae_naive_h3"
  ],
  "status": "supported",
  "caveat": "Overlapping 3-step errors; the difference is very small."
 },
 {
  "id": "C3",
  "text": "The h=1 loss difference is statistically significant by the Diebold-Mariano test (p about 0.02); the h=3 difference is not (p about 0.28).",
  "results_keys": [
   "dm_stat_h1",
   "dm_pvalue_h1",
   "dm_stat_h3",
   "dm_pvalue_h3"
  ],
  "status": "supported",
  "caveat": "The DM test is not designed for nested models and the forecasts are nearly identical, so the p-values are approximate."
 },
 {
  "id": "C4",
  "text": "35 of the 36 origin pairs per horizon were evaluated, because the 2025-10-01 observation is missing.",
  "results_keys": [
   "n_evaluated_h1",
   "n_evaluated_h3",
   "n_origins",
   "data_issues"
  ],
  "status": "supported",
  "caveat": ""
 },
 {
  "id": "C5",
  "text": "The estimated AR coefficients on monthly changes in the last window are close to zero, so the model's forecasts are nearly identical to naive.",
  "results_keys": [
   "ar1_coef_last_window",
   "ar2_coef_last_window"
  ],
  "status": "supported",
  "caveat": "Probably influenced by the 2020 COVID outlier kept in the sample."
 }
]