SPB Git

spb/wp2_uqo Public

UQO Working Paper No. 2 — Decoding Real Estate Descriptions: text-based hedonic analysis of housing listings.

researcheconomicshousinghedonicnlpuqo
TeX 73.8% Python 26%

Complete bibliography audit (100% verified) + README refresh

- Final sweep of the 38 remaining entries: 3 fixes (Halvorsen-Pollakowski 1981
  JUE replaces mismatched Halvorsen-Palmquist 1980 AER metadata; Irwin 2002
  Land Economics open-space paper replaces Irwin-Bockstael; Goodman-Thibodeau
  1995 heteroskedasticity paper replaces 1998 segmentation mismatch).
- Des Rosiers et al. (2002) landscaping premium range verified (4-12%) and
  stated precisely in the discussion.
- ~700-character description truncation confirmed empirically in the raw DB
  (pile-up at 701-703, mid-word cuts before GST/QST boilerplate).
- README: 53-page badge, '86 verified references' badge, new docs in tree.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
simon-pierre boucher committed 5 days ago (Aug 5, 2026) parent 545f4a0

Showing 7 changed files with +68 and −39

modified README.md +7 −4
@@ -21,7 +21,8 @@
21 21 [![Reproducible](https://img.shields.io/badge/Reproducible-end--to--end%20pipeline-2E7D32?style=flat-square&logo=githubactions&logoColor=white)](#-reproducing-everything)
22 22 [![Sample](https://img.shields.io/badge/n-17%2C087%20houses-1565C0?style=flat-square)](#-data)
23 23 [![Model](https://img.shields.io/badge/Adj.%20R%C2%B2-0.452%20%E2%86%92%200.511-6A1B9A?style=flat-square)](#-key-results)
24 −[![Paper](https://img.shields.io/badge/Paper-47%20pages%20PDF-B71C1C?style=flat-square&logo=adobeacrobatreader&logoColor=white)](paper/main.pdf)
24 +[![Paper](https://img.shields.io/badge/Paper-53%20pages%20PDF-B71C1C?style=flat-square&logo=adobeacrobatreader&logoColor=white)](paper/main.pdf)
25 +[![References](https://img.shields.io/badge/References-86%20verified%20(OpenAlex%20%2B%20DOI)-00695C?style=flat-square&logo=googlescholar&logoColor=white)](paper/references.bib)
25 26 [![JEL](https://img.shields.io/badge/JEL-R31%20%C2%B7%20C45%20%C2%B7%20C21%20%C2%B7%20R21-455A64?style=flat-square)](#-citation)
26 27
27 28 </div>
@@ -134,6 +135,8 @@ wp2_uqo/
134 135 ├── README.md ← you are here
135 136 ├── AUDIT.md ← forensic audit of the original (pre-restructuring) project
136 137 ├── CHANGES.md ← everything that was moved / refactored / corrected, with diffs
138 +├── PAPER_REVIEW.md ← critical pre-upgrade assessment of the paper's scholarship
139 +├── UPGRADE_REPORT.md ← literature expansion: refs added/replaced, claims flagged
137 140 ├── requirements.txt ← pinned dependencies (exact versions used for verification)
138 141 │
139 142 ├── data/ ← NOT tracked by git (see data/README.md)
@@ -160,11 +163,11 @@ wp2_uqo/
160 163 ├── results/ ← model & robustness outputs (CSV, versioned)
161 164 │
162 165 └── paper/ ← LaTeX source (UQO working-paper style)
163 − ├── main.tex │ metadata + section inputs (47-page PDF)
166 + ├── main.tex │ metadata + section inputs (53-page PDF)
164 167 ├── preamble.tex │ packages, layout, custom macros
165 168 ├── main.pdf │ compiled paper (committed for convenience)
166 169 ├── Makefile │ latexmk build
167 − ├── references.bib │ 59 entries, all cited keys resolve
170 + ├── references.bib │ 86 entries, every one verified (OpenAlex + DOI)
168 171 ├── sections/ │ titlepage · intro · literature · methodology · data ·
169 172 │ │ results · robustness · discussion · conclusion · appendix
170 173 └── tables/ │ 7 machine-generated + 3 hand-maintained booktabs tables
@@ -219,7 +222,7 @@ python3 scripts/04_robustness.py # full robustness battery (~4 min)
219 222 python3 scripts/05_figures.py # all 11 figures
220 223 python3 scripts/06_tables.py # LaTeX tables from results
221 224
222 −cd paper && latexmk -pdf main.tex # 47-page PDF, 0 errors
225 +cd paper && latexmk -pdf main.tex # 53-page PDF, 0 errors
223 226 ```
224 227
225 228 Expected checkpoints along the way:
modified UPGRADE_REPORT.md +26 −2
@@ -86,11 +86,35 @@ Plus replacements listed in §1 (Goodwin ×2, Zhu, Baur, Law, Alfano, Hong, Delm
86 86 ## 4. Claims flagged for your verification
87 87
88 88 1. ~~Levitt & Syverson 3.7% figure~~ — **resolved**: verified against the published REStat paper (90(4), 599–611; agents' own homes sell 3.7% higher and stay 9.5 days longer on the market). The existing bib entry is correct.
89 −2. **Des Rosiers et al. (2002) "mid-single-digit landscaping premiums"** — direction and venue verified; the "mid-single-digit" characterization is from the paper's well-known results but should be checked against the article text.
90 −3. **"Descriptions truncated at ~700 characters"** — a property of this data export (empirically true in our sample: max 703); confirm it is the platform/export doing the truncation before attributing it publicly.
89 +2. ~~Des Rosiers et al. (2002) magnitude~~ — **resolved**: the paper reports landscaping premiums of roughly 4% (hedges ~3.6–3.9%, landscaped curbs ~4.4%) up to ~12.4% (landscaped patio). The discussion sentence now states this verified range ("roughly 4% to about 12%").
90 +3. ~~"Descriptions truncated at ~700 characters"~~ — **resolved**: confirmed in the raw database. House/land/plex remarks pile up at 701–703 characters and are cut mid-word before an appended GST/QST boilerplate notice (e.g. "…z bien. GST/QST must be added to the asking price"), which is the signature of a hard excerpt cap at the source. The paper's wording ("truncated at approximately 700 characters in the data export") is accurate.
91 91 4. The softened Conneau et al. sentence ("material performance losses") replaced the previous unverifiable "up to 15%" figure.
92 92 5. The MiniLM "Spearman 0.82 on STS-B / 5× faster" claims were replaced by a softer, cited statement (Wang et al. 2020; Muennighoff et al. 2023).
93 93
94 +## 4bis. Completion of the audit — 100% of the bibliography now verified
95 +
96 +A final sweep verified the remaining 38 entries (the seminal econometrics and
97 +NLP works). 35 were correct as written. Three needed fixes, now applied:
98 +
99 +- `halvorsen1981choice` — the entry contained the metadata of a *different*
100 + real paper (Halvorsen & Palmquist 1980, AER, on dummy variables in semilog
101 + equations). The paper the text relies on (choice of functional form for
102 + hedonic equations) is Halvorsen & **Pollakowski** 1981, *Journal of Urban
103 + Economics* 10(1), 37–49 — corrected.
104 +- `irwin2002interacting` → `irwin2002effects` — the entry pointed to Irwin &
105 + Bockstael's spatial-externalities paper, but the text cites it for the value
106 + of open space; replaced with Irwin (2002), "The Effects of Open Space on
107 + Residential Property Values", *Land Economics* 78(4), 465–480.
108 +- `goodman1998housing` → `goodman1995age` — the entry (Goodman & Thibodeau
109 + 1998, market segmentation) was a mismatch for the heteroskedasticity claim it
110 + supported; replaced with Goodman & Thibodeau (1995), "Age-Related
111 + Heteroskedasticity in Hedonic House Price Equations", *J. Housing Research*
112 + 6(1), 25–42.
113 +
114 +With these fixes, **every one of the 86 bibliography entries has been verified**
115 +against OpenAlex and/or the publisher's record, and every cited claim was
116 +checked against what the cited work actually shows.
117 +
94 118 ## 5. Literature potentially in tension with the paper
95 119
96 120 - **Shen & Ross (2021)** and **Baur et al. (2023)** obtain larger predictive gains from unrestricted text representations than our 20 projections — consistent with our own PCA benchmark; the paper now states this openly ("departure from the prediction-first literature") instead of claiming fit superiority.
modified paper/main.pdf +0 −0

Binary file not shown.

modified paper/references.bib +32 −30
@@ -106,36 +106,6 @@
106 106 pages = {6894--6910}
107 107 }
108 108
109 −@article{goodman1998housing,
110 − author = {Goodman, Allen C. and Thibodeau, Thomas G.},
111 − title = {Housing Market Segmentation},
112 − journal = {Journal of Housing Economics},
113 − year = {1998},
114 − volume = {7},
115 − number = {2},
116 − pages = {121--143}
117 −}
118 −
119 −@article{halvorsen1981choice,
120 − author = {Halvorsen, Robert and Palmquist, Raymond},
121 − title = {The Interpretation of Dummy Variables in Semilogarithmic Equations},
122 − journal = {American Economic Review},
123 − year = {1980},
124 − volume = {70},
125 − number = {3},
126 − pages = {474--475}
127 −}
128 −
129 −@article{irwin2002interacting,
130 − author = {Irwin, Elena G. and Bockstael, Nancy E.},
131 − title = {Interacting Agents, Spatial Externalities and the Evolution of Residential Land Use Patterns},
132 − journal = {Journal of Economic Geography},
133 − year = {2002},
134 − volume = {2},
135 − number = {1},
136 − pages = {31--54}
137 −}
138 −
139 109 @article{koenker1978regression,
140 110 author = {Koenker, Roger and Bassett, Gilbert W.},
141 111 title = {Regression Quantiles},
@@ -910,3 +880,35 @@
910 880 pages = {101658},
911 881 doi = {10.1016/j.compenvurbsys.2021.101658}
912 882 }
883 +
884 +@article{halvorsen1981choice,
885 + author = {Halvorsen, Robert and Pollakowski, Henry O.},
886 + title = {Choice of Functional Form for Hedonic Price Equations},
887 + journal = {Journal of Urban Economics},
888 + year = {1981},
889 + volume = {10},
890 + number = {1},
891 + pages = {37--49},
892 + doi = {10.1016/0094-1190(81)90021-8}
893 +}
894 +
895 +@article{irwin2002effects,
896 + author = {Irwin, Elena G.},
897 + title = {The Effects of Open Space on Residential Property Values},
898 + journal = {Land Economics},
899 + year = {2002},
900 + volume = {78},
901 + number = {4},
902 + pages = {465--480},
903 + doi = {10.2307/3146847}
904 +}
905 +
906 +@article{goodman1995age,
907 + author = {Goodman, Allen C. and Thibodeau, Thomas G.},
908 + title = {Age-Related Heteroskedasticity in Hedonic House Price Equations},
909 + journal = {Journal of Housing Research},
910 + year = {1995},
911 + volume = {6},
912 + number = {1},
913 + pages = {25--42}
914 +}
modified paper/sections/discussion.tex +1 −1
@@ -10,7 +10,7 @@ Our results establish that free-text property descriptions contain economically
10 10
11 11 The positive effects of \textbf{Modern/Contemporary} (+16.4\%) and \textbf{Luxury} (+14.2\%) language align with theoretical expectations and prior empirical work on quality premiums \citep{nowak2017quality, goodwin2014broker}. These dimensions capture aspects of housing quality---design aesthetics, material quality, technological amenities---that are simply not reflected in counts of bedrooms and bathrooms. A house with three bathrooms can range from a modest home with basic fixtures to a luxury property with spa-like en-suites; the listing description captures this variation. The quantile regression analysis (Section~\ref{sec:robustness}) reveals that the luxury premium is amplified in the upper portion of the price distribution, consistent with the notion that luxury is a positional good whose marginal value increases with baseline quality \citep{frank2007falling} and with the general finding of the quantile-hedonic literature that many quality attributes command larger implicit prices in upper market segments \citep{zietz2007determinants}.
12 12
13 −The \textbf{Land \& Nature} premium (+13.0\%) reflects the well-documented value of natural amenities and outdoor space in residential markets \citep{irwin2002interacting, tyrvainen2005benefits}. This finding is particularly relevant in the Quebec context: using Quebec City transactions and geocoded measures, \citet{desrosiers2002landscaping} estimate that superior landscaping and mature vegetation add mid-single-digit percentages to house values. Our text-based measure recovers an amenity gradient of the same sign through the listing narrative alone, without geocoded proximity data---evidence that the two measurement strategies tap the same underlying valuation.
13 +The \textbf{Land \& Nature} premium (+13.0\%) reflects the well-documented value of natural amenities and outdoor space in residential markets \citep{irwin2002effects, tyrvainen2005benefits}. This finding is particularly relevant in the Quebec context: using Quebec City transactions and site-inspection measures, \citet{desrosiers2002landscaping} estimate landscaping premiums ranging from roughly 4\% (hedges, landscaped curbs) to about 12\% (a landscaped patio) of house value. Our text-based measure recovers an amenity gradient of comparable direction and magnitude through the listing narrative alone, without site-level amenity data---evidence that the two measurement strategies tap the same underlying valuation.
14 14
15 15 The negative coefficient on \textbf{Family-Friendly} ($-$11.6\%) deserves careful interpretation. This does not imply that schools and parks reduce property values; rather, it reflects the systematic association between family-oriented marketing language and lower-priced suburban markets. After controlling for structural characteristics, family-friendly language serves as a residual proxy for suburban location where prices are lower. This is precisely the equilibrium-sorting logic emphasized by \citet{kuminoff2013new}: households sort across locations on price and amenities jointly, so language that marks a market segment inherits that segment's price level. The finding also echoes \citet{delmelle2021language}, who show that property-advertisement text is a strong predictor of neighborhood socioeconomic composition: listing language is as much about \textit{where} a property is as about \textit{what} it is. This illustrates the importance of interpreting hedonic coefficients as conditional marginal effects rather than causal estimates---a point emphasized by \citet{pakes2003reconsideration} in the broader context of hedonic identification.
16 16
modified paper/sections/literature.tex +1 −1
@@ -16,7 +16,7 @@ In the housing context, the hedonic approach yields the canonical specification:
16 16 \end{equation}
17 17 where $P_i$ is the price of property $i$, $\bfX_i$ is a vector of structural, locational, and neighborhood attributes, and $\bfbeta$ captures the implicit marginal prices. The semi-logarithmic functional form, recommended by \citet{halvorsen1981choice} and widely adopted in the literature, allows coefficients to be interpreted as approximate percentage changes in price for a unit change in the characteristic. \citet{cropper1988choice} evaluated alternative functional forms through Monte Carlo experiments, finding that simpler parametric specifications (linear and log-linear) outperform flexible Box-Cox transformations when variables are measured with error or important attributes are omitted.
18 18
19 −The empirical literature on hedonic housing models is vast. \citet{sirmans2005composition} surveyed the composition of hedonic models and identified bedrooms, bathrooms, lot size, age, square footage, and proximity to central business districts as the most frequently included variables. \citet{sirmans2006empirical} conducted a meta-analysis of 64 hedonic studies, finding that bathrooms, square footage, and lot size consistently exhibit the largest marginal effects. \citet{malpezzi2003hedonic} provided a comprehensive review of methodological issues, including functional form selection, spatial autocorrelation, and multicollinearity. Two extensions of the baseline framework are particularly relevant here. First, \textit{quantile hedonics}: \citet{zietz2007determinants} show that the implicit prices of housing attributes vary systematically across the conditional price distribution, with many characteristics valued more highly in upper price segments, and \citet{mcmillen2008changes} uses quantile methods to decompose changes in the entire distribution of house prices. Our quantile analysis in Section~\ref{sec:robustness} extends this logic to text-derived characteristics. Second, \textit{spatial hedonics}: housing data are spatially dependent, and a long literature---\citet{anselin1988spatial}, \citet{dubin1988estimation}, and \citet{can1992specification} among the foundations---has developed specifications that absorb spatial autocorrelation in prices and errors; \citet{dube2014spatial} adapt these methods to the Canadian and Quebec microdata context. Closer to our setting still, a sustained research program using Quebec City transactions has quantified the capitalization of property attributes ranging from landscaping to accessibility \citep{desrosiers2002landscaping}. In the amenity-capitalization literature more broadly, \citet{cheshire2004capitalisation} demonstrate school-quality capitalization in local housing markets and \citet{gibbons2014costs} documents the discount associated with visual environmental disamenities, while \citet{irwin2002interacting} and \citet{tyrvainen2005benefits} establish the positive value of open space and urban vegetation.
19 +The empirical literature on hedonic housing models is vast. \citet{sirmans2005composition} surveyed the composition of hedonic models and identified bedrooms, bathrooms, lot size, age, square footage, and proximity to central business districts as the most frequently included variables. \citet{sirmans2006empirical} conducted a meta-analysis of 64 hedonic studies, finding that bathrooms, square footage, and lot size consistently exhibit the largest marginal effects. \citet{malpezzi2003hedonic} provided a comprehensive review of methodological issues, including functional form selection, spatial autocorrelation, and multicollinearity. Two extensions of the baseline framework are particularly relevant here. First, \textit{quantile hedonics}: \citet{zietz2007determinants} show that the implicit prices of housing attributes vary systematically across the conditional price distribution, with many characteristics valued more highly in upper price segments, and \citet{mcmillen2008changes} uses quantile methods to decompose changes in the entire distribution of house prices. Our quantile analysis in Section~\ref{sec:robustness} extends this logic to text-derived characteristics. Second, \textit{spatial hedonics}: housing data are spatially dependent, and a long literature---\citet{anselin1988spatial}, \citet{dubin1988estimation}, and \citet{can1992specification} among the foundations---has developed specifications that absorb spatial autocorrelation in prices and errors; \citet{dube2014spatial} adapt these methods to the Canadian and Quebec microdata context. Closer to our setting still, a sustained research program using Quebec City transactions has quantified the capitalization of property attributes ranging from landscaping to accessibility \citep{desrosiers2002landscaping}. In the amenity-capitalization literature more broadly, \citet{cheshire2004capitalisation} demonstrate school-quality capitalization in local housing markets and \citet{gibbons2014costs} documents the discount associated with visual environmental disamenities, while \citet{irwin2002effects} and \citet{tyrvainen2005benefits} establish the positive value of open space and urban vegetation.
20 20
21 21 A persistent challenge in hedonic pricing is the omitted variable bias arising from unobserved quality attributes. \citet{pakes2003reconsideration} argued that standard hedonic regressions yield biased implicit price estimates when important product characteristics are unobservable to the econometrician but observable to market participants. This concern is directly relevant to our study: listing descriptions may convey quality information---about finish materials, maintenance history, or neighborhood ambiance---that is not captured by conventional structural variables but is fully observable to buyers.
22 22
modified paper/sections/robustness.tex +1 −1
@@ -8,7 +8,7 @@ To assess the sensitivity of our findings to modeling assumptions, sample compos
8 8
9 9 \subsection{Heteroskedasticity Diagnostics}
10 10
11 −The Breusch-Pagan test \citep{breusch1979simple} applied to Model~D strongly rejects the null hypothesis of homoskedasticity (LM $= 768.0$, $p < 0.001$). This result formally justifies our use of HC3 heteroskedasticity-consistent standard errors throughout. The pattern of heteroskedasticity---residual variance increasing at both tails of the fitted value distribution (Figure~\ref{fig:diagnostics}, panel a)---is typical of housing price models and reflects the greater price dispersion in both the lowest-quality and highest-quality segments of the market \citep{goodman1998housing}.
11 +The Breusch-Pagan test \citep{breusch1979simple} applied to Model~D strongly rejects the null hypothesis of homoskedasticity (LM $= 768.0$, $p < 0.001$). This result formally justifies our use of HC3 heteroskedasticity-consistent standard errors throughout. The pattern of heteroskedasticity---residual variance increasing at both tails of the fitted value distribution (Figure~\ref{fig:diagnostics}, panel a)---is typical of housing price models and reflects the greater price dispersion in both the lowest-quality and highest-quality segments of the market \citep{goodman1995age}.
12 12
13 13 \subsection{Variance Inflation Factors}
14 14
15 15