% ==========================================================================
\section{Variable Definitions}
\label{sec:app_variables}
% ==========================================================================

Table~\ref{tab:app_variables} defines every variable used in the paper
and indicates whether it comes from a structured field of the scrape or
is parsed from the card title.

\begin{table}[!htbp]
\centering
\caption{Variable Definitions}
\label{tab:app_variables}
\begin{threeparttable}
\small
\begin{tabular}{p{4.1cm}p{8.3cm}l}
\toprule
Variable & Definition & Source \\
\midrule
\multicolumn{3}{l}{\textit{Dependent variable}} \\
$\ln p$ & Natural log of the displayed price (CAD), winsorised at the 1st/99th percentiles of the priced sample & field \\
\midrule
\multicolumn{3}{l}{\textit{Structural}} \\
$\ln$ bedrooms & Log of the bedroom count; studios recoded to one & field, title \\
$\ln(1+\text{bathrooms})$ & Log of one plus the bathroom count; zeros repaired from the title; half bath $= 0.5$ & field, title \\
$\ln$ guests & Log of the guest capacity (minimum one) & field \\
Shared bathroom & 1 if the title reads ``shared bath'' & title \\
Studio & 1 if the title reads ``Studio'' & title \\
Title category & Six classes of the 44 host-chosen labels (reference: Rental unit) & title \\
\midrule
\multicolumn{3}{l}{\textit{Presentation}} \\
$\ln(1+\text{amenities})$ & Log of one plus the number of amenities listed & field \\
$\ln(1+\text{photos})$ & Log of one plus the number of photos & field \\
Pets allowed & 1 if pets are allowed & field \\
\midrule
\multicolumn{3}{l}{\textit{Host and reputation}} \\
Superhost & 1 if the host holds the Superhost badge & field \\
Guest Favourite & 1 if the listing holds the Guest Favourite badge & field \\
$\ln(1+\text{reviews})$ & Log of one plus the number of reviews & field \\
Rated & 1 if a star rating is displayed (0 for ``New'' and unrated cards) & title \\
Rating $-$ 4.8 & Displayed rating minus 4.8, set to zero for unrated listings & title \\
\midrule
\multicolumn{3}{l}{\textit{Location}} \\
$\ln(1+\text{km to centre})$ & Log of one plus the great-circle distance (km) to the nearest of 22 reference municipalities & coordinates \\
$\ln(1+\text{listings within 1 km})$ & Log of one plus the number of other priced listings within 1~km & coordinates \\
Montreal & 1 if the municipality is Montreal & field \\
City / cell fixed effects & Indicator for the municipality (if $\geq 15$ listings) or for one of 25 $k$-means cells of the remaining listings & field, coordinates \\
\midrule
\multicolumn{3}{l}{\textit{Regime classification}} \\
$\hat p_i$ & Posterior probability of the stay-price regime from Equation~\eqref{eq:mixture} & estimated \\
\bottomrule
\end{tabular}
\begin{tablenotes}
\footnotesize
\item \textit{Notes:} ``Field'' denotes a structured field of the
scrape; ``title'' denotes a value parsed from the listing-card title.
The scraper's price category, rating category and composite quality
score are not used.
\end{tablenotes}
\end{threeparttable}
\end{table}

% ==========================================================================
\section{Additional Results}
\label{sec:app_results}
% ==========================================================================

Table~\ref{tab:app_stay_logit} reports a logistic regression of the
mixture classification on listing characteristics, estimated on the full
priced sample, which describes the profile of listings whose displayed
price is a stay price. Table~\ref{tab:app_vif} reports variance inflation
factors for the M4 regressors.

\begin{table}[!htbp]
\centering
\caption{Which Listings Display a Stay Price? Logistic Regression of the Regime Classification}
\label{tab:app_stay_logit}
\begin{threeparttable}
\small
\input{../results/tables/rev_stay_logit.tex}
\begin{tablenotes}
\footnotesize
\item \textit{Notes:} Dependent variable: 1 if the listing is classified
in the stay regime ($\hat p_i \geq 0.5$). Robust (HC1) standard errors.
Average marginal effects are averaged over the sample. Reference title
category: Rental unit. ***, ** and * denote significance at the 1, 5 and
10\% levels.
\end{tablenotes}
\end{threeparttable}
\end{table}

\begin{table}[!htbp]
\centering
\caption{Variance Inflation Factors, Specification M4}
\label{tab:app_vif}
\begin{threeparttable}
\small
\input{../results/tables/rev_vif.tex}
\begin{tablenotes}
\footnotesize
\item \textit{Notes:} Variance inflation factors computed on the M4
design matrix (analysis sample, $N = 2{,}480$). Values below 5 indicate
that collinearity among the capacity variables does not compromise the
precision of the estimates.
\end{tablenotes}
\end{threeparttable}
\end{table}