1[2 {"id":"C1","text":"Over 60 origins (2021-09 to 2026-08, h=1), the ridge forecast has RMSE 0.561 and MAE 0.451 percent per month, the naive forecast 0.883/0.699 and the expanding mean 0.544/0.429.","results_keys":["rmse_ridge","mae_ridge","rmse_naive","mae_naive","rmse_mean","mae_mean","n_origins"],"status":"supported","caveat":"Current-vintage data; publication lags ignored."},3 {"id":"C2","text":"Ridge improves on the naive forecast by 36.5% in RMSE, and the Diebold-Mariano test rejects equal accuracy (p=0.0014).","results_keys":["rel_improvement_vs_naive","dm_stat_ridge_vs_naive","dm_pvalue_ridge_vs_naive"],"status":"supported","caveat":"60 targets; the DM test ignores parameter-estimation effects."},4 {"id":"C3","text":"Ridge does not beat the expanding historical mean: its RMSE is 3.1% higher (and its MAE is also higher); the difference is not statistically significant (DM p=0.59).","results_keys":["rel_improvement_vs_mean","rmse_ridge","rmse_mean","mae_ridge","mae_mean","dm_stat_ridge_vs_mean","dm_pvalue_ridge_vs_mean"],"status":"supported","caveat":"Only lambda=50 was evaluated, as specified; the ranking may depend on lambda and on the treatment of 2020 outliers."},5 {"id":"C4","text":"All standardisation statistics and the target mean were computed from each origin's training window only (expanding), with 413 training rows at the last origin.","results_keys":["normalisation_window","n_analysed"],"status":"supported","caveat":"Verified by a test that perturbs future data (out/state/checks.md)."}6]7