1{2 "task_id": "F1-conf-03",3 "n_analysed": 1800,4 "n_firms": 300,5 "predictors_used": [6 "leverage",7 "cash_ratio",8 "log_sales"9 ],10 "variables_excluded": [11 {12 "variable": "rating_2025",13 "reason": "Known only in 2025 and constructed from realised default history through 2022 and sample-average leverage; violates end-of-year-t availability rule (outcome leakage)."14 },15 {16 "variable": "default_next",17 "reason": "Outcome variable (known end of t+1); dependent variable, not a predictor."18 },19 {20 "variable": "firm_id",21 "reason": "Identifier; used only for clustering standard errors, not as a regressor."22 },23 {24 "variable": "year",25 "reason": "Origin-year index; not part of the specified model, used only to identify firm-years."26 }27 ],28 "beta_leverage": 0.2637836102938267,29 "se_leverage_cluster": 0.0407569280434615,30 "r2": 0.03490564212216729,31 "default_rate": 0.12111111111111111,32 "feasibility": "complete",33 "feasibility_reason": null,34 "data_issues": [35 {36 "issue": "40 rows are exact duplicates of another row (duplicated firm_id-year keys, identical on all columns).",37 "handling": "Dropped duplicate copies, keeping one row per firm-year (exclusion step 2)."38 },39 {40 "issue": "default_next empty for 300 de-duplicated rows, all in origin year(s) [2022] (outcome beyond the end-2022 data cut).",41 "handling": "Excluded from estimation; not imputed (exclusion step 3)."42 },43 {44 "issue": "rating_2025 is a final-vintage field built from realised defaults (all defaults carry rating D) - look-ahead leakage.",45 "handling": "Column removed from analytic dataset and listed in variables_excluded (exclusion step 1)."46 },47 {48 "issue": "Some firms have default_next = 1 in several years (default not absorbing in the panel).",49 "handling": "Kept as recorded; codebook does not define default as absorbing. Noted as a limitation."50 },51 {52 "issue": "leverage bounded exactly at 0.02 and 0.95 (possible truncation in the source).",53 "handling": "Kept as recorded; noted as a limitation."54 }55 ],56 "n_input_rows": {57 "firm_panel.csv": 214058 },59 "random_seed": null,60 "supplementary": {61 "intercept": 0.08997926409935522,62 "beta_cash_ratio": -0.18594837465723182,63 "beta_log_sales": -0.007342181807581363,64 "se_cash_ratio_cluster": 0.0588860837664576,65 "se_log_sales_cluster": 0.007626106514531905,66 "ci95_leverage_cluster": [67 0.18390149920815163,68 0.3436657213795017469 ],70 "p_leverage_cluster": 9.663918872288981e-11,71 "se_leverage_hc1": 0.03744708748506851,72 "n_clusters": 300,73 "cluster_se_note": "statsmodels cluster-robust covariance with default small-sample correction (G/(G-1))*((N-1)/(N-K)); CI uses normal critical values."74 }75}