spb/wp3_uqo Public

1% Author: Simon-Pierre Boucher — contact@spboucher.ai2%3% ============================================================================4% UQO Working Paper No. 35% Hedonic Housing Price Models for the United States: A Multi-Method6% Comparison of Parametric, Quantile, and Machine Learning Approaches7% ============================================================================8\documentclass[12pt,letterpaper]{article}910% --- Encoding & Language ---11\usepackage[utf8]{inputenc}12\usepackage[T1]{fontenc}13\usepackage[english]{babel}1415% --- Page Layout ---16\usepackage[letterpaper, margin=1in, headheight=15pt]{geometry}17\usepackage{setspace}18\onehalfspacing19\setlength{\parindent}{1.5em}20\setlength{\parskip}{0pt}2122% --- Typography ---23\usepackage{newtxtext,newtxmath}24\usepackage{amsmath,amsfonts}25\let\Bbbk\relax26\usepackage{amssymb}27\usepackage{mathtools}28\usepackage{microtype}2930% --- Tables ---31\usepackage{booktabs}32\usepackage{threeparttable}33\usepackage{tabularx}34\usepackage{array}35\usepackage{multirow}36\usepackage{longtable}37\usepackage{adjustbox}38\usepackage{siunitx}39\usepackage{dcolumn}4041% --- Figures ---42\usepackage{graphicx}43\graphicspath{{./}{../}}  % figures live in ../figures/, logo in ./44\usepackage[45  font       = small,46  labelfont  = bf,47  labelsep   = period,48  skip       = 8pt,49  justification = justified,50  singlelinecheck = false51]{caption}52\usepackage{subcaption}53\usepackage{float}54\usepackage{pdflscape}5556% --- Colors & Links ---57\usepackage[dvipsnames]{xcolor}58\definecolor{linkblue}{RGB}{0,51,102}59\usepackage[bookmarks, bookmarksnumbered]{hyperref}60\hypersetup{61  colorlinks  = true,62  linkcolor   = NavyBlue,63  citecolor   = NavyBlue,64  urlcolor    = NavyBlue,65  pdftitle    = {Hedonic Housing Price Models for the United States: A Multi-Method Comparison of Parametric, Quantile, and Machine Learning Approaches},66  pdfauthor   = {Simon-Pierre Boucher}67}6869% --- Bibliography ---70\usepackage[round, authoryear, comma]{natbib}71\setcitestyle{aysep={,}}72\bibliographystyle{apalike}7374% --- Headers & Footers ---75\usepackage{fancyhdr}76\pagestyle{fancy}77\fancyhf{}78\fancyhead[L]{\small\itshape Hedonic Housing Price Models for the United States}79\fancyhead[R]{\small\thepage}80\renewcommand{\headrulewidth}{0.4pt}81\renewcommand{\footrulewidth}{0pt}82\fancypagestyle{plain}{%83  \fancyhf{}84  \fancyfoot[C]{\small\thepage}85  \renewcommand{\headrulewidth}{0pt}86}8788% --- Section Formatting ---89\usepackage{titlesec}90\titleformat{\section}{\large\bfseries}{\thesection.}{0.5em}{}91\titleformat{\subsection}{\normalsize\bfseries}{\thesubsection.}{0.5em}{}92\titleformat{\subsubsection}{\normalsize\itshape}{\thesubsubsection.}{0.5em}{}9394% --- Appendix Support ---95\usepackage[toc, page]{appendix}96\usepackage{enumitem}97\usepackage{etoolbox}98\usepackage[hang,flushmargin]{footmisc}99100% --- Custom Column Types ---101\newcolumntype{R}[1]{>{\raggedleft\arraybackslash}p{#1}}102\newcolumntype{L}[1]{>{\raggedright\arraybackslash}p{#1}}103\newcolumntype{C}[1]{>{\centering\arraybackslash}p{#1}}104\newcolumntype{d}[1]{D{.}{.}{#1}}105106% --- Custom Commands ---107\newcommand{\sym}[1]{\ensuremath{^{#1}}}108\newcommand{\stmark}[1]{\rlap{\textsuperscript{#1}}}109\DeclareMathOperator*{\plim}{plim}110\newcommand{\E}{\mathbb{E}}111\newcommand{\Var}{\mathrm{Var}}112\newcommand{\Cov}{\mathrm{Cov}}113\newcommand{\Corr}{\mathrm{Corr}}114\newcommand{\se}{\mathrm{s.e.}}115\newcommand{\tr}{\mathrm{tr}}116\newcommand{\rank}{\mathrm{rank}}117\newcommand{\diag}{\mathrm{diag}}118\newcommand{\R}{\mathbb{R}}119\newcommand{\N}{\mathbb{N}}120\newcommand{\eps}{\varepsilon}121\newcommand{\bfbeta}{\boldsymbol{\beta}}122\newcommand{\bfgamma}{\boldsymbol{\gamma}}123\newcommand{\bfalpha}{\boldsymbol{\alpha}}124\newcommand{\bfdelta}{\boldsymbol{\delta}}125\newcommand{\bftheta}{\boldsymbol{\theta}}126\newcommand{\bfSigma}{\boldsymbol{\Sigma}}127\newcommand{\bfOmega}{\boldsymbol{\Omega}}128\newcommand{\bfX}{\mathbf{X}}129\newcommand{\bfY}{\mathbf{Y}}130\newcommand{\bfy}{\mathbf{y}}131\newcommand{\bfe}{\mathbf{e}}132\newcommand{\bfs}{\mathbf{s}}133\newcommand{\iid}{\overset{\mathrm{iid}}{\sim}}134\newcommand{\pto}{\overset{p}{\to}}135\newcommand{\dto}{\overset{d}{\to}}136\newcommand{\ols}{\mathrm{OLS}}137\newcommand{\iv}{\mathrm{IV}}138\newcommand{\gmm}{\mathrm{GMM}}139\newcommand{\mle}{\mathrm{MLE}}140\newcommand{\pval}{\textit{p}-value}141\newcommand{\tstat}{\textit{t}-statistic}142\newcommand{\fstat}{\textit{F}-statistic}143\newcommand{\tablenote}[1]{\begin{minipage}{\linewidth}\footnotesize #1\end{minipage}}144\newcommand{\signote}{*** $p < 0.001$; ** $p < 0.01$; * $p < 0.05$.}145146% ============================================================================147% METADATA148% ============================================================================149\newcommand{\WPnumber}{3}150\newcommand{\WPtitle}{Hedonic Housing Price Models for the United States: A Multi-Method Comparison of Parametric, Quantile, and Machine Learning Approaches}151\newcommand{\WPsubtitle}{}152\newcommand{\WPdate}{May 2026}153\newcommand{\WPversion}{1.1}154\newcommand{\WPabstract}{%155This paper compares econometric and machine-learning approaches to hedonic housing valuation using 788,842 active Zillow listings across all 50 U.S.\ states and the District of Columbia. A semi-log OLS model with 62 regressors ($R^2 = 0.634$) provides interpretable listing-price gradients; adding ZIP3 fixed effects raises $R^2$ to 0.725, and Moran's $I = 0.27$ confirms strong residual spatial autocorrelation. Quantile regression reveals distributional heterogeneity, with inter-quantile Wald tests rejecting coefficient equality between $\tau = 0.10$ and $\tau = 0.90$ for 11 of 13 key variables. XGBoost achieves $R^2 = 0.833$ under random validation but only 0.425 under state-level geographic holdout; ablation analysis traces the predictive gain primarily to neighborhood-quality features ($+17.6$ pp) and shows that removing geographic features \emph{improves} geographic holdout $R^2$ to 0.519, revealing spatial overfitting. SHAP importance rankings are stable across models (Spearman $\rho > 0.89$). Robustness checks confirm that the lot-size gradient triples when imputed observations are dropped, while other coefficients remain stable under winsorization and subsampling. Throughout, estimates are interpreted as conditional associations in listing prices, not causal willingness-to-pay parameters.%156}157\newcommand{\WPkeywords}{hedonic pricing, housing markets, quantile regression, XGBoost, SHAP, spatial autocorrelation, geographic validation}158\newcommand{\WPjel}{R31, C21, C45, C52}159160% --- Author ---161\newcommand{\WPauthor}{Simon-Pierre Boucher}162\newcommand{\WPaffiliation}{%163  D\'epartement des sciences administratives\\164  Universit\'e du Qu\'ebec en Outaouais%165}166\newcommand{\WPemail}{simon-pierre.boucher@uqo.ca}167\newcommand{\WPaddress}{%168  Gatineau -- Pavillon Alexandre-Tach\'e\\169  283, boulevard Alexandre-Tach\'e\\170  Gatineau, Qu\'ebec, Canada J9A 1L8%171}172173% ============================================================================174% DOCUMENT175% ============================================================================176\begin{document}177178% --- Title Page ---179\input{sections/titlepage}180181% --- Main Body ---182\input{sections/introduction}183\input{sections/literature}184\input{sections/data}185\input{sections/methodology}186\input{sections/results}187\input{sections/robustness}188\input{sections/discussion}189\input{sections/limitations}190\input{sections/conclusion}191192% --- References ---193\newpage194\addcontentsline{toc}{section}{References}195\bibliography{references}196197% --- Appendix ---198\newpage199\input{appendix/appendix}200201\end{document}202