Repository Public Research preview
1% Auto-generated by scripts/18_revision_language_leakage_spatial.py (2026-10-17)2\begin{table}[htbp]3 \centering4 \begin{threeparttable}5 \caption{Gains from the AI Feature Layers by Language, Platform, and Presence of a Price in the Text}6 \label{tab:rob_language_source}7 \small8 \begin{tabular}{@{}lcccc@{}}9 \toprule10 Subsample & $N$ & $R^2$ base & $\Delta R^2$ text (pp) & $\Delta R^2$ vision (pp) \\11 \midrule12 \multicolumn{5}{@{}l}{\textit{Panel A: In-sample $R^2$, Model~A (measured area), municipality FE}} \\[2pt]13 All listings & 9{,}446 & 0.717 & +0.8 & +3.0 \\14 \quad French descriptions & 2{,}619 & 0.704 & +1.5 & +3.4 \\15 \quad English descriptions & 4{,}815 & 0.763 & +0.6 & +2.2 \\16 \quad Mixed / bilingual & 2{,}012 & 0.579 & +3.2 & +4.8 \\17 \quad Realtor.ca (no asking price in text) & 5{,}781 & 0.779 & +0.6 & +2.4 \\18 \quad DuProprio (asking price in text) & 3{,}665 & 0.564 & +3.3 & +4.1 \\19 \quad Realtor.ca, no dollar amount in text & 5{,}640 & 0.780 & +0.6 & +2.4 \\20 All listings, RTA fixed effects & 9{,}446 & 0.722 & +0.7 & +3.2 \\21 \addlinespace22 \multicolumn{5}{@{}l}{\textit{Panel B: Out-of-sample $R^2$ (5-fold, random), OLS, full sample}} \\[2pt]23 All listings & 19{,}123 & 0.619 & +0.8 & +5.8 \\24 \quad French & 8{,}529 & 0.622 & +1.2 & +4.8 \\25 \quad English & 8{,}250 & 0.562 & +0.7 & +7.9 \\26 \quad Realtor.ca & 15{,}356 & 0.701 & +0.6 & +3.9 \\27 \quad DuProprio & 3{,}767 & $-0.083$ & +2.8 & +22.8 \\28 \addlinespace29 \multicolumn{5}{@{}l}{\textit{Panel C: Out-of-sample $R^2$ (5-fold, random), gradient boosting, full sample}} \\[2pt]30 All listings & 19{,}123 & 0.729 & +1.4 & +2.7 \\31 \quad French & 8{,}529 & 0.680 & +1.5 & +3.1 \\32 \quad English & 8{,}250 & 0.737 & +1.5 & +2.6 \\33 \quad Realtor.ca & 15{,}356 & 0.748 & +1.2 & +2.6 \\34 \quad DuProprio & 3{,}767 & 0.564 & +3.1 & +2.8 \\35 \bottomrule36 \end{tabular}37 \begin{tablenotes}[flushleft]38 \footnotesize39 \item \textit{Notes:} Panel~A re-estimates the nested in-sample ablation of Model~A (structural, amenity, room, and40 listing controls with municipality and type fixed effects; then $+$ LLM text layer; then $+$ façade vision layer) on41 each subsample; ``$\Delta R^2$'' is the gain, in percentage points, from adding the layer. Language is classified42 from French and English stop-word counts (ratio rule of 1.5; ``mixed'' listings are mostly DuProprio descriptions that43 concatenate an English translation and the French original). Every DuProprio description contains the asking price44 (``Asking Price \$\dots''); 2.5\% of Realtor.ca45 descriptions contain some dollar amount (usually a municipal assessment, a renovation budget, or a tax; the 14146 Model~A listings concerned are too few for a separate regression). Panels~B and47 C evaluate the full-sample cross-validated predictions (Table~\ref{tab:ablation}, identical folds) within each48 subsample; the base is the structural $+$ amenity $+$ rooms $+$ listing specification. Within-subsample $R^2$49 values can be negative (DuProprio, OLS) when the pooled model is miscalibrated for the subsample.50 \end{tablenotes}51 \end{threeparttable}52\end{table}53