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": "becomes known in 2025; built from realised default history through 2022 and average leverage over the sample -> violates end-of-year-t information rule (outcome leakage)"14 },15 {16 "variable": "default_next",17 "reason": "outcome variable (known end of year t+1); used only as dependent variable"18 },19 {20 "variable": "firm_id",21 "reason": "identifier; used only for clustering"22 },23 {24 "variable": "year",25 "reason": "origin-year index; not a regressor in the specified model"26 }27 ],28 "beta_leverage": 0.2637836102938267,29 "se_leverage_cluster": 0.04075692804346149,30 "r2": 0.03490564212216729,31 "default_rate": 0.12111111111111111,32 "feasibility": "complete",33 "feasibility_reason": null,34 "data_issues": [35 {36 "issue": "40 exact duplicate rows (same firm_id, year and all values)",37 "handling": "dropped; first copy kept, giving one row per firm-year (300 firms x 7 years)"38 },39 {40 "issue": "default_next missing for 300 unique firm-years (origin years [2022]: outcome year 2023 after the end-2022 data cut)",41 "handling": "excluded from estimation, not imputed"42 },43 {44 "issue": "leverage takes the value 0.02 exactly in 57 unique firm-years (minimum of the variable), suggesting bottom-coding/censoring at 0.02",45 "handling": "kept as recorded; noted as limitation (cannot recover true values)"46 },47 {48 "issue": "rating_2025 is a final-vintage (2025) field constructed from realised default history and sample-average leverage; it is perfectly informative of default here (all defaults occur in rating D)",49 "handling": "excluded from the analytic dataset as look-ahead leakage"50 }51 ],52 "n_input_rows": {53 "firm_panel.csv": 214054 },55 "random_seed": null,56 "extra": {57 "ci95_leverage": [58 0.18390149920815163,59 0.3436657213795017460 ],61 "p_leverage": 9.663918872288908e-11,62 "params": {63 "Intercept": 0.08997926409935522,64 "leverage": 0.2637836102938267,65 "cash_ratio": -0.18594837465723182,66 "log_sales": -0.00734218180758136367 },68 "se_cluster": {69 "Intercept": 0.04351602070943619,70 "leverage": 0.04075692804346149,71 "cash_ratio": 0.058886083766457535,72 "log_sales": 0.00762610651453185173 },74 "se_cluster_note": "statsmodels cluster-robust (CR1 with small-sample correction), 300 clusters"75 }76}