1{2 "record_id": "a072fb43e67fcc553e457777f0c68324ace19eb7",3 "eligible": true,4 "exclusion_reason": null,5 "study": {6 "title": "Factors influencing housing prices: A comparative study using multiple linear regression and random forest",7 "year": 2024,8 "doi": "10.54254/2753-8818/51/2024ch0174",9 "country": "unknown (stated as United States)",10 "region_city": "unknown",11 "sample_start": null,12 "sample_end": null,13 "property_type": "unknown",14 "price_type": "listing",15 "data_source": "Kaggle 'Housing Price Prediction' dataset (Harish Kumar, 2023), 545 observations, 13 variables",16 "document_type": "conference",17 "estimators": [18 "OLS"19 ],20 "spatial_method": "none",21 "time_fe": false,22 "location_fe": false,23 "se_type": "OLS",24 "n_obs_total": 544,25 "ai_methods": [26 "random_forest (prediction comparison only, RMSE/MAPE; no marginal effects)"27 ],28 "notes": "Theoretical and Natural Science, Proceedings of CONF-MPCS 2024 Workshop; student conference paper. The Kaggle dataset has no documented geography, currency or period (widely regarded as not US data); price type assumed listing. Recommend quality-tier exclusion / human review. Random forest reported only for predictive accuracy (RMSE 0.2095 vs 0.2032 for MLR; MAPE 0.0108 vs 0.0104)."29 },30 "models": [31 {32 "model_id": "T2-c1",33 "table": "2",34 "column": "1",35 "page": 4,36 "dep_var": "log housing price (currency not stated; dataset labelled 'US')",37 "dep_transform": "log",38 "estimator": "OLS",39 "n_obs": 544,40 "r2": 0.697,41 "se_or_t_in_parentheses": "none",42 "sample_subset": "Full Kaggle 'Housing Price Prediction' dataset after removing 1 outlier (545 -> 544); adjusted R2 0.6896, RSE 0.2059; SE, t, p, VIF printed in columns"43 }44 ],45 "coefficients": [46 {47 "model_id": "T2-c1",48 "var_name_printed": "Area",49 "taxonomy_id": "living_area",50 "x_transform": "level",51 "x_unit": "sqft",52 "beta": 5e-05,53 "se": null,54 "t": 10.579,55 "p": null,56 "p_stars": "",57 "ci_lo": null,58 "ci_hi": null,59 "page": 4,60 "confidence": "medium",61 "notes": "p printed as '< 0.0001'; Area of house in square feet; SE printed as '< 0.0001' (not recorded); Kaggle toy dataset of unverifiable provenance (compiled 'from various websites', published 2023; country/period unknown, paper labels it US)"62 },63 {64 "model_id": "T2-c1",65 "var_name_printed": "Bedrooms",66 "taxonomy_id": "bedrooms",67 "x_transform": "level",68 "x_unit": "count",69 "beta": 0.029,70 "se": 0.014,71 "t": 2.046,72 "p": 0.041,73 "p_stars": "",74 "ci_lo": null,75 "ci_hi": null,76 "page": 4,77 "confidence": "medium",78 "notes": "Kaggle toy dataset of unverifiable provenance (compiled 'from various websites', published 2023; country/period unknown, paper labels it US)"79 },80 {81 "model_id": "T2-c1",82 "var_name_printed": "Bathrooms",83 "taxonomy_id": "bathrooms",84 "x_transform": "level",85 "x_unit": "count",86 "beta": 0.262,87 "se": 0.02,88 "t": 8.121,89 "p": null,90 "p_stars": "",91 "ci_lo": null,92 "ci_hi": null,93 "page": 4,94 "confidence": "medium",95 "notes": "p printed as '< 0.0001'; Kaggle toy dataset of unverifiable provenance (compiled 'from various websites', published 2023; country/period unknown, paper labels it US)"96 },97 {98 "model_id": "T2-c1",99 "var_name_printed": "Stories",100 "taxonomy_id": "storeys",101 "x_transform": "level",102 "x_unit": "count",103 "beta": 0.09,104 "se": 0.012,105 "t": 7.264,106 "p": null,107 "p_stars": "",108 "ci_lo": null,109 "ci_hi": null,110 "page": 4,111 "confidence": "medium",112 "notes": "p printed as '< 0.0001'; Kaggle toy dataset of unverifiable provenance (compiled 'from various websites', published 2023; country/period unknown, paper labels it US)"113 },114 {115 "model_id": "T2-c1",116 "var_name_printed": "Main Road",117 "taxonomy_id": "other",118 "x_transform": "binary",119 "x_unit": "binary",120 "beta": 0.118,121 "se": 0.027,122 "t": 4.312,123 "p": null,124 "p_stars": "",125 "ci_lo": null,126 "ci_hi": null,127 "page": 4,128 "confidence": "medium",129 "notes": "p printed as '< 0.0001'; House accessible from the main road (yes/no); Kaggle toy dataset of unverifiable provenance (compiled 'from various websites', published 2023; country/period unknown, paper labels it US)"130 },131 {132 "model_id": "T2-c1",133 "var_name_printed": "Guestroom",134 "taxonomy_id": "other",135 "x_transform": "binary",136 "x_unit": "binary",137 "beta": 0.071,138 "se": 0.025,139 "t": 2.812,140 "p": 0.005,141 "p_stars": "",142 "ci_lo": null,143 "ci_hi": null,144 "page": 4,145 "confidence": "medium",146 "notes": "House has a guest room; Kaggle toy dataset of unverifiable provenance (compiled 'from various websites', published 2023; country/period unknown, paper labels it US)"147 },148 {149 "model_id": "T2-c1",150 "var_name_printed": "Basement",151 "taxonomy_id": "basement",152 "x_transform": "binary",153 "x_unit": "binary",154 "beta": 0.091,155 "se": 0.021,156 "t": 4.293,157 "p": null,158 "p_stars": "",159 "ci_lo": null,160 "ci_hi": null,161 "page": 4,162 "confidence": "medium",163 "notes": "p printed as '< 0.0001'; Kaggle toy dataset of unverifiable provenance (compiled 'from various websites', published 2023; country/period unknown, paper labels it US)"164 },165 {166 "model_id": "T2-c1",167 "var_name_printed": "Hot Water Heating",168 "taxonomy_id": "heating",169 "x_transform": "binary",170 "x_unit": "binary",171 "beta": 0.164,172 "se": 0.043,173 "t": 3.814,174 "p": 0.0002,175 "p_stars": "",176 "ci_lo": null,177 "ci_hi": null,178 "page": 4,179 "confidence": "medium",180 "notes": "Hot water heating system; Kaggle toy dataset of unverifiable provenance (compiled 'from various websites', published 2023; country/period unknown, paper labels it US)"181 },182 {183 "model_id": "T2-c1",184 "var_name_printed": "Airconditioning",185 "taxonomy_id": "air_conditioning",186 "x_transform": "binary",187 "x_unit": "binary",188 "beta": 0.173,189 "se": 0.021,190 "t": 8.298,191 "p": null,192 "p_stars": "",193 "ci_lo": null,194 "ci_hi": null,195 "page": 4,196 "confidence": "medium",197 "notes": "p printed as '< 0.0001'; Kaggle toy dataset of unverifiable provenance (compiled 'from various websites', published 2023; country/period unknown, paper labels it US)"198 },199 {200 "model_id": "T2-c1",201 "var_name_printed": "Parking",202 "taxonomy_id": "parking",203 "x_transform": "level",204 "x_unit": "count",205 "beta": 0.044,206 "se": 0.011,207 "t": 3.872,208 "p": null,209 "p_stars": "",210 "ci_lo": null,211 "ci_hi": null,212 "page": 4,213 "confidence": "medium",214 "notes": "p printed as '< 0.0001'; Number of parking spaces; Kaggle toy dataset of unverifiable provenance (compiled 'from various websites', published 2023; country/period unknown, paper labels it US)"215 },216 {217 "model_id": "T2-c1",218 "var_name_printed": "Prefer area",219 "taxonomy_id": "other",220 "x_transform": "binary",221 "x_unit": "binary",222 "beta": 0.123,223 "se": 0.022,224 "t": 5.5,225 "p": null,226 "p_stars": "",227 "ci_lo": null,228 "ci_hi": null,229 "page": 4,230 "confidence": "medium",231 "notes": "p printed as '< 0.0001'; House located in a preferred area (yes/no); Kaggle toy dataset of unverifiable provenance (compiled 'from various websites', published 2023; country/period unknown, paper labels it US)"232 },233 {234 "model_id": "T2-c1",235 "var_name_printed": "Semi-furnished",236 "taxonomy_id": "other",237 "x_transform": "dummy",238 "x_unit": "binary",239 "beta": 0.021,240 "se": 0.023,241 "t": 0.92,242 "p": 0.358,243 "p_stars": "",244 "ci_lo": null,245 "ci_hi": null,246 "page": 4,247 "confidence": "medium",248 "notes": "Furnishing status dummy, reference = fully furnished; Kaggle toy dataset of unverifiable provenance (compiled 'from various websites', published 2023; country/period unknown, paper labels it US)"249 },250 {251 "model_id": "T2-c1",252 "var_name_printed": "Unfurnished",253 "taxonomy_id": "other",254 "x_transform": "dummy",255 "x_unit": "binary",256 "beta": -0.108,257 "se": 0.024,258 "t": -4.416,259 "p": null,260 "p_stars": "",261 "ci_lo": null,262 "ci_hi": null,263 "page": 4,264 "confidence": "medium",265 "notes": "p printed as '< 0.0001'; Furnishing status dummy, reference = fully furnished; Kaggle toy dataset of unverifiable provenance (compiled 'from various websites', published 2023; country/period unknown, paper labels it US)"266 }267 ]268}