Paper: arXiv 2507.21298
Authors: Harrison Katz, Erica Savage
Abstract
Using all U.S. Airbnb reservations created in 2019-2024 (booking-count weighted), we quantify pandemic-era shifts in nights per booking (NPB) and the mechanism behind them. The mean rose from 3.68 pre-COVID to 4.36 during restrictions and stabilized near 4.07 post-2021 (about 10% above 2019); the booking-weighted median moved from 2 to 3 nights. A two-parameter log-normal fits best by wide AIC/BIC margins, indicating heavy tails. A negative-binomial model with month effects implies post-vaccine bookings are 6.5% shorter than restriction-era bookings, while pre-COVID bookings are 16% shorter. In a two-part model at 28 nights, the booking share of month-plus stays rose from 1.43% (pre) to 2.72% (restriction) and settled at 2.04% (post); conditional means among long stays were about 55-60 nights. Thus the higher average reflects more long stays rather than longer long stays. A SARIMA(0,1,1)(0,1,1)12 with pandemic-phase dummies improves fit (LR=8.39, df=2, p=0.015), consistent with a structural level shift.
Complexity vs Empirical Score
- Math Complexity: 7.0/10
- Empirical Rigor: 8.0/10
- Quadrant: Holy Grail — high math complexity, high empirical rigor
Why this score: The paper employs advanced statistical modeling including SARIMA, negative-binomial regression, and distributional fitting (log-normal) with AIC/BIC comparisons, while using the entire U.S. Airbnb booking dataset (2019–2024) with booking-weighted data and multiple robustness checks.
Research Flowchart
flowchart TD
A["Research Goal: Quantify pandemic-era shifts<br>in Airbnb booking length (2019-2024)"] --> B["Data: U.S. Airbnb Reservations<br>(Booking-Count Weighted)"]
B --> C["Methodology: Distributional &<br>Time-Series Analysis"]
C --> D["Statistical Modeling"]
subgraph D ["Computational Processes"]
D1["Log-Normal Fit<br>Heavy Tails"] --> D2["Negative-Binomial<br>Post-vaccine effect: -6.5%"]
D1 --> D3["Two-Part Model<br>>28 nights: Share ↑"]
D1 --> D4["SARIMA (0,1,1)(0,1,1)12<br>Structural Level Shift"]
end
D --> E["Key Findings"]
subgraph E ["Outcomes"]
F["Mean NPB Rose 10%<br>(3.68 → 4.07)"]
G["Median Shifted<br>(2 → 3 nights)"]
H["Increase driven by<br>more long stays, not longer tails"]
end
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper provides national‑scale, booking‑weighted evidence that U.S. short‑term‑rental stays became durably longer and more heavy‑tailed after 2020, filling a gap in tourism and revenue‑management literature.
Source sentence
The paper provides national-scale, booking-weighted evidence that U.S. short-term-rental stays became durably longer and more heavy-tailed after 2020, filling a gap in the tourism and revenue-management literature.
Assumes 5
- Bookings longer than 180 nights are excluded to avoid undue influence of extreme outliers. data
Source sentence
Upper-tail exclusion. Bookings longer than 180 nights are excluded to focus on the short- and medium-term rental product (and to avoid conflating long-term tenancy/relocation leases).
- Reservations are collapsed into booking‑count weights for weighted statistics. statistical
Source sentence
Weighted statistics and likelihoods recover population frequencies while reducing computational load.
- A two‑parameter log‑normal distribution adequately captures the heavy‑tailed stay‑length distribution. model
Source sentence
A two-parameter log-normal fits best by wide AIC/BIC margins, indicating heavy tails.
- Three pandemic phases (pre‑COVID, restriction, post‑vaccine) capture the national‑level discontinuity. other
Source sentence
Our coarse three-phase coding captures the national-level discontinuity but not the staggered state-by-state lockdowns, partial re-openings, and rollbacks.
Show 1 more
- Weighted means/quantiles summarize the realized booking population without model assumptions. statistical
Source sentence
Weighted means/quantiles summarize the realized booking population without model assumptions.
Data
- U.S. Airbnb reservations (booking‑count weighted) alternative commercial
Source sentence
Using all U.S. Airbnb reservations created in 2019-2024 (booking-count weighted), we quantify pandemic-era shifts in nights per booking (NPB) and the mechanism behind them.
Costs
Not applicable
Finds 5
- The mean stay length rose from 3.68 nights pre‑COVID to 4.36 during restrictions and stabilized near 4.07 post‑2021, about 10% above the 2019 baseline. statistical
Source sentence
The mean rose from 3.68 pre-COVID to 4.36 during restrictions and stabilized near 4.07 post-2021 (about 10% above 2019);
- The booking‑weighted median increased from 2 to 3 nights. statistical
Source sentence
the booking-weighted median moved from 2 to 3 nights.
- The share of month‑plus stays rose from 1.43% pre‑COVID to 2.72% during restrictions and settled at 2.04% post‑COVID, driving the higher average stay length. statistical
Source sentence
the booking share of month-plus stays rose from 1.43% (pre) to 2.72% (restriction) and settled at 2.04% (post);
- A SARIMA(0,1,1)(0,1,1)12 with pandemic‑phase dummies improves fit (LR=8.39, df=2, p=0.015), indicating a structural level shift. statistical
Source sentence
A SARIMA(0,1,1)(0,1,1)12 with pandemic-phase dummies improves fit (LR=8.39, df=2, p=0.015), consistent with a structural level shift.
- Negative‑binomial model estimates post‑vaccine bookings are 6.5% shorter than restriction‑era bookings, while pre‑COVID bookings are 16% shorter. statistical
Source sentence
a negative-binomial model with month effects implies post-vaccine bookings are 6.5% shorter than restriction-era bookings, while pre-COVID bookings are 16% shorter.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 22 related papers). Coverage is partial, so this is neither replication nor refutation.
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.
Cited References (88)
- Determinants of tourists’ length of stay (2021) — link
- R: A Language and Environment for Statistical Computing (2023) — link
- fitdistrplus: An R Package for Fitting Distributions (2015) — link
- Modern Applied Statistics with S (2002) — link
- matrixStats: Functions that Apply to Rows and Columns of Matrices (and to Vectors) (2025) — link
- Lead times in flux: Analyzing Airbnb booking dynamics during global Upheavals (2018–2022) — → 2501.10535
- fable: Forecasting Models for Tidy Time Series (2021) — link
- Welcome to the tidyverse (2019) — link
and 80 more
- Regression Analysis of Count Data (2013) — link
- Distance matters: The impact of physical and relative distance on pleasure tourists’ length of stay in Barbados (2020) — link
- What Makes Our Stay Longer or Shorter? A Study on Macau (2021) — link
- A bibliometric analysis of length of stay studies in tourism (2022) — link
- Exploring the Factors Involved in Tourists’ Decision-Making and Determinants of Length of Stay (2023) — link
- Bimodal length of stay in the accommodation sharing economy (2023) — link
- Length of stay for tourists’ inland trips (2018) — link
- Digital nomads – a quest for holistic freedom in work and leisure (2018) — link
- In search of a digital nomad: defining the phenomenon (2020) — link
- Digital Nomadism: the nexus of remote working and travel mobility (2020) — link
- Emergent geographies of digital nomadism: conceptual framing, insights and implications for tourism (2025) — link
- Moving with and against the state: digital nomads and frictional mobility regimes (2024) — link
- A Bayesian Dirichlet auto-regressive moving average model for forecasting lead times (2024) — link
- The potential stickiness of pandemic-induced behavior changes in the United States (2021) — link
- Typologizing Digital Nomad Visas: Comparing Policy Rationales from Tourism to Wealth Accumulation to Immigration (2024) — link
- Digital Nomadism and the Emergence of Digital Nomad Visas: What Policy Objectives Do States Aim to Achieve? (2025) — link
- Forecasting: Principles and Practice (2021) — link
- Dynamic regression models (2021) — link
- Intervention Analysis with Applications to Economic and Environmental Problems (1975) — link
- Determinants of tourists’ length of stay at various tourist attractions based on cellular data (2020) — link
- Digital nomads’ lifestyles and coworkation: a research agenda (2021) — link
- Working from anywhere? Work from here! Approaches to attract digital nomads (2024) — link
- Typologizing Digital Nomad Visas: Comparing Policy Rationales from Tourism to Wealth Accumulation to Immigration (2024) — link
- Digital Nomadism and the Emergence of Digital Nomad Visas: What Policy Objectives Do States Aim to Achieve? (2025) — link
- Moving with and against the state: digital nomads and frictional mobility regimes (2024) — link
- Emergent geographies of digital nomadism: conceptual framing, insights and implications for tourism (2025) — link
- Digital Nomads (2020) — link
- A B ayesian D irichlet A uto- R egressive C onditional H eteroskedasticity M odel for C ompositional T ime S eries (2025) — link
- Airbnb customer experience in longterm stays: a structural topic model and ChatGPT-driven analysis of the reviews of remote workers (2024) — link
- Specification and Testing of Some Modified Count Data Models (1986) — link
- Some Statistical Models for Limited Dependent Variables with Application to the Demand for Durable Goods (1971) — link
- The Length of Stay in the Demand for Tourism (2006) — link
- A Latent Class Approach to Tourists’ Length of Stay (2011) — link
- Determinant Factors of Senior Tourists’ Length of Stay (2014) — link
- Factors Explaining Length of Stay: Lessons to Be Learnt from Madeira Island (2021) — link
- The Impact of COVID‑19 on Tourists’ Length of Stay and Daily Expenditures (2021) — link
- What Makes Our Stay Longer or Shorter? A Study on Macau (2021) — link
- Determinants of Tourists’ Length of Stay: A Hurdle Count Data Approach (2019) — link
- Repeat Tourism in Uruguay: Modelling Truncated Distributions of Count Data (2014) — link
- Econometric Models Based on Count Data: Comparisons and Applications of Some Estimators and Tests (1986) — link
- Regression Analysis of Count Data (1998) — link
- Consumer valuation of Airbnb listings: a hedonic pricing approach (2017) — link
- A Note on Certain Discrete Mixed Distributions (1966) — link
- The Determinants of Length of Stay of Tourists in the Azores (2008) — link
- Actuarial Modelling of Claim Counts: Risk Classification, Credibility and Bonus–Malus Systems (2009)
- Trust and Reputation in the Sharing Economy: The Role of Personal Photos in Airbnb (2016) — link
- Low‑Cost Travel and Tourism Expenditures (2016) — link
- Zero‑Inflated Generalized Poisson Regression Model with an Application to Domestic Violence Data (2006) — link
- Series mensuales de entradas de turistas y excursionistas. Islas Canarias 2012–2021 (Metodolog' \i a 2016) (2021)
- Determinants of Length of Stay: A Practical Use of Survival Analysis (2007) — link
- Modelling bimodality of length of tourist stay (2019) — link
- Quasi‑Binomial Zero‑Inflated Regression Model Suitable for Variables with Bounded Support (2020) — link
- A Bimodal Discrete Shifted Poisson Distribution: A Case Study of Tourists’ Length of Stay (2020) — link
- Tourist Tax to Promote Rentals of Low‑Emission Vehicles (2021) — link
- Global Trends in Length of Stay: Implications for Destination Management and Climate Change (2018) — link
- Excess Zeros in Count Models for Recreational Trips (1996) — link
- A Bivariate Count Data Model for Household Tourism Demand (2006) — link
- Encuestas de alojamiento tur' \i stico (2021)
- Encuestas de alojamiento tur' \i stico (2022)
- The structural changes of a local tourism network: comparison of before and after COVID-19 (2021) — link
- Zero-Inflated Poisson Regression, with an Application to Defects in Manufacturing (1992)
- A Zero‑and‑One Inflated Poisson Model and Its Application (2018) — link
- Length of stay for low-cost tourism (2008) — link
- Tourist Environment and Online Reputation as a Generator of Added Value in the Sharing Economy: The Case of Airbnb in Urban and Sun‑and‑Beach Holiday Destinations (2019) — link
- Exploring Word‑of‑Mouth Influences on Travel Decisions: Friends and Relatives vs.\ Other Travellers (2007) — link
- Taxing Tourism: The Case of Rental Cars in Mallorca (2007) — link
- Past experience, traveler personality and tripographics on intention to use Airbnb (2017) — link
- Length of Stay: Evidence from Santiago de Compostela (2018) — link
- Length of Stay: Price and Income Semi‑Elasticities at Different Destinations in Italy (2012) — link
- Uncertainty and Expectations in Portugal’s Tourism Activities: Impacts of COVID‑19 (2021) — link
- Length of Stay at Multiple Destinations of Tourism Trips in Brazil (2015) — link
- Estimating spatial effects on peer-to-peer accommodation prices: Towards an innovative hedonic model approach (2019) — link
- Analyzing tourists’ length of stay at destinations with survival models: A constructive critique based on a case study (2012) — link
- Impacts of Peer‑to‑Peer Accommodation Use on Travel Patterns (2016) — link
- Generating Reliable Tourist Accommodation Statistics: Bootstrapping Regression Model for Overdispersed Long‑Tailed Data (2020) — link
- Likelihood Ratio Tests for Model Selection and Non‑Nested Hypotheses (1989) — link
- Price Determinants of Sharing Economy‑Based Accommodation Rental: A Study of Listings from 33 Cities on Airbnb.com (2017) — link
- Modeling Tourists’ Length of Stay: Does One Model Fit All? (2015) — link
- Properties of the Zero‑and‑One Inflated Poisson Distribution and Likelihood‑Based Inference Methods (2016) — link
- Afraid to Travel after COVID‑19 ? Self‑Protection, Coping and Resilience against Pandemic ‘Travel Fear’ (2021) — link
1 of 88 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.