spb/wp2_uqo Public

1% Author: Simon-Pierre Boucher — contact@spboucher.ai2%3\begin{table}[!htbp]4\centering5\caption{Comparison of text representation methods in the hedonic model. $\Delta R^2$ is the improvement over Model~A (structural only, $R^2 = 0.452$).}6\label{tab:text_comparison}7\small8\begin{adjustbox}{max width=\textwidth}9\begin{tabular}{lR{1.5cm}C{2.2cm}C{2.6cm}}10\toprule11\textbf{Text Representation} & $\boldsymbol{\Delta R^2}$ & \textbf{Interpretability} & \textbf{Economic Usefulness} \\12\midrule13Description length only & +0.012 & High & Low \\14PCA on embeddings (20 PC) & +0.070 & None & Low \\15PCA on embeddings (20 PC) + length & +0.078 & None & Low \\16Reference cosine (20 dim) & +0.044 & High & High \\17\textbf{Reference cosine (20 dim) + length} & \textbf{+0.060} & \textbf{High} & \textbf{High} \\18\bottomrule19\multicolumn{4}{p{0.95\textwidth}}{\footnotesize{\textit{Notes:} All specifications include the six structural variables and are estimated on the same $n = 17{,}087$ sample. The 20 principal components capture 49.5\% of the variance of the raw 384-dimensional embeddings. PCA achieves a larger fit improvement than the reference projections but produces features with no economic interpretation; the reference-based approach trades roughly two percentage points of $R^2$ for coefficient-level interpretability (see Section~\ref{sec:robustness}).}} \\20\end{tabular}21\end{adjustbox}22\end{table}23