Paper: arXiv 2410.16526
Authors: Osman Doğan, Raffaele Mattera, Philipp Otto, Süleyman Taşpınar
Abstract
We introduce a dynamic spatiotemporal volatility model that extends traditional approaches by incorporating spatial, temporal, and spatiotemporal spillover effects, along with volatility-specific observed and latent factors. The model offers a more general network interpretation, making it applicable for studying various types of network spillovers. The primary innovation lies in incorporating volatility-specific latent factors into the dynamic spatiotemporal volatility model. Using Bayesian estimation via the Markov Chain Monte Carlo (MCMC) method, the model offers a robust framework for analyzing the spatial, temporal, and spatiotemporal effects of a log-squared outcome variable on its volatility. We recommend using the deviance information criterion (DIC) and a regularized Bayesian MCMC method to select the number of relevant factors in the model. The model’s flexibility is demonstrated through two applications: a spatiotemporal model applied to the U.S. housing market and another applied to financial stock market networks, both highlighting the model’s ability to capture varying degrees of interconnectedness. In both applications, we find strong spatial/network interactions with relatively stronger spillover effects in the stock market.
Complexity vs Empirical Score
- Math Complexity: 9.0/10
- Empirical Rigor: 6.0/10
- Quadrant: Holy Grail — high math complexity, high empirical rigor
Why this score: The paper introduces a novel spatiotemporal ARCH model with latent factors, requiring advanced Bayesian MCMC estimation, finite mixture approximations, and regularization techniques, indicating very high mathematical density. The empirical rigor is solid, featuring a rigorous Bayesian framework, model selection criteria (DIC), a simulation study, and two real-world financial applications (housing and stock markets) demonstrating model fit and spillover detection, making it backtest-ready but not heavily focused on implementation details like code or live trading metrics.
Research Flowchart
flowchart TD G["Research Goal: Model Dynamic Spatiotemporal Volatility with Latent Factors"] --> M["Methodology: Dynamic Spatiotemporal & Network ARCH Model"] M --> D["Data: U.S. Housing & Stock Market Networks"] D --> C["Process: Bayesian MCMC Estimation<br>DIC & Regularized Selection"] C --> O["Outcome: Captured Network Spillovers<br>Stronger in Financial Markets"]
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 proposes a dynamic spatiotemporal volatility model that incorporates spatial, temporal, and spatiotemporal spillover effects together with volatility‑specific observed and latent factors.
Source sentence
We introduce a dynamic spatiotemporal volatility model that extends traditional approaches by incorporating spatial, temporal, and spatiotemporal spillover effects, along with volatility‑specific observed and latent factors.
Assumes 5
- The spatial autoregressive parameter ρ follows a Uniform(−1,1) prior. model
Source sentence
Therefore, we assume that ρ ∼Uniform(−1, 1).
- Latent factors ft are drawn from a standard multivariate normal distribution. statistical
Source sentence
we assume that ft ∼N(0, Iq), where Iq is the q × q identity matrix.
- The distribution of log‑squared error terms is approximated by a ten‑component normal mixture. statistical
Source sentence
we approximate the distribution of the log‑squared error terms in the transformed model using a finite mixture of normal distributions.
- Stability conditions on ρ and φ as stated in Section 2 must hold. model
Source sentence
the prior distributions of ρ and φ are subject to the stability condition stated in Section 2.
Show 1 more
- The number of latent factors q is selected by the lowest DIC value. model
Source sentence
we choose the q value that yields the lowest DIC criterion, specifically selecting the model with q = 7 latent factors.
Data
- Quarterly US house price indexes macro public
Source sentence
between 1975 and 2023. The data source is the Federal Housing Finance Agency website.
Costs
Not applicable
Finds 5
- Both applications reveal strong spatial/network interactions, with spillover effects stronger in the stock market than in housing. statistical
Source sentence
In both applications, we find strong spatial/network interactions with relatively stronger spillover effects in the stock market.
- Estimated spatial and spatiotemporal effects in the US housing market are ρ=0.16 and δ=0.19, indicating similar magnitude of instantaneous and lagged spillovers. statistical
Source sentence
The estimates of ρ and δ are 0.16 and 0.19, respectively.
- The temporal effect γ is positive and statistically significant, showing volatility persistence over time. statistical
Source sentence
The estimated temporal effect (γ) is positive and statistically significant across all models.
- The DIC criterion selects a model with seven latent factors (q=7) as optimal. statistical
Source sentence
the model with q = 7 latent factors.
- Simulation results demonstrate that posterior median estimates are close to true parameter values and credible intervals are precise. statistical
Source sentence
both estimation algorithms report posterior median estimates that are close to the true values. The 95% credible interval estimates indicate evidence for the precision of the suggested estimation algorithms.
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 (146)
- Spatial aggregation, spatial dependence and predictability in the UK housing market (1996)
- Estimation of log-GARCH models in the presence of zero returns (2018)
- Network log-ARCH models for forecasting stock market volatility — → 2303.11064
- On the network topology of variance decompositions: Measuring the connectedness of financial firms (2014)
- Efficient factor GARCH models and factor-DCC models (2009)
- Correlation and network analysis of global financial indices (2012)
- Clustering and information in correlation based financial networks (2004)
- Behavioral finance impacts on US stock market volatility: an analysis of market anomalies (2024)
and 138 more
- Generalized autoregressive conditional heteroskedasticity (1986)
- A spatio-temporal model of house prices in the USA (2010)
- Further evidence on the spatio-temporal model of house prices in the U nited S tates (2014)
- Regional housing price cycles: A spatio-temporal analysis using US state-level data (2011)
- The spatial diffusion of regional housing prices across US states (2014)
- Modelling regional house prices (2011)
- A changepoint analysis of UK house price spillovers (2023)
- Understanding housing market volatility (2015)
- Integrated deviance information criterion for spatial autoregressive models with heteroskedasticity (2024)
- Observed-data DIC for spatial panel data models (2023)
- Multivariate simultaneous generalized ARCH (1995)
- Information criteria for matrix exponential spatial specifications (2023)
- A multivariate spatial and spatiotemporal ARCH model (2024)
- A general framework for spatial GARCH models (2023)
- Bayesian inference in spatial stochastic volatility models: An application to house price returns in Chicago (2021)
- Housing price forecastability: A factor analysis (2018)
- Common factors and spatial dependence: an application to US house prices (2021)
- Modeling US housing prices by spatial dynamic structural equation models (2013)
- Generalized dynamic factor models and volatilities: estimation and forecasting (2017)
- Spatial effects and house price dynamics in the USA (2016)
- Spatiotemporal analysis of German real-estate prices (2018)
- Spatial spillovers in emerging market spreads (2013)
- Public debt, investment and economic growth dynamics: Do geographical proximity and spatial spillover effects matter? (2024)
- Proximity and growth spillovers in European regions: The role of geographical, economic and technological linkages (2015)
- Generalized dynamic factor models and volatilities: recovering the market volatility shocks (2016)
- Level and volatility factors in macroeconomic data (2017)
- Factor structure in commodity futures return and volatility (2019)
- Dynamic conditional correlation: A simple class of multivariate generalized autoregressive conditional heteroskedasticity models (2002)
- A class of stochastic volatility models for environmental applications (2011)
- Bayesian inference in spatial GARCH models: an application to US house price returns (2023)
- Daily house price indices: Construction, modeling, and longer-run predictions (2016)
- On business cycle asymmetries in G7 countries (2004)
- Stock market volatility: Identifying major drivers and the nature of their impact (2015)
- Correlation, hierarchies, and networks in financial markets (2010)
- Asset allocation with a high dimensional latent factor stochastic volatility model (2006)
- Clustering huge number of financial time series: A panel data approach with high-dimensional predictors and factor structures (2017)
- A latent factor model for forecasting realized variances (2021)
- Trans-Atlantic equity volatility connectedness: US and European financial institutions, 2004–2014 (2015)
- Range-based estimation of stochastic volatility models (2002)
- Consistent ranking of volatility models (2006)
- Spatial GARCH models for unknown spatial locations–an application to financial stock returns (2024)
- A computer movie simulating urban growth in the D etroit region (1970)
- An intra-city analysis of house price convergence and spatial dependence (2021)
- A pair-wise analysis of intra-city price convergence within the Paris housing market (2017)
- Inter-city transport infrastructure and intra-city housing markets: Estimating the redistribution effect of high-speed rail in Shenzhen, China (2021)
- Directional spatial autoregressive dependence in the conditional first-and second-order moments (2021)
- Efficient GMM estimation of high order spatial autoregressive models with autoregressive disturbances (2010)
- Inference on higher-order spatial autoregressive models with increasingly many parameters (2015)
- Local quantile house price indices (2014)
- A two-step approach to account for unobserved spatial heterogeneity (2017)
- Quantile house price indices in Beijing (2017)
- Regional House Prices and the Ripple Effect: A New Interpretation (1999)
- Simple diagnostic tests for spatial dependence (1996)
- Asymptotic Distributions of Quasi-Maximum Likelihood Estimators for Spatial Autoregressive Models (2004)
- GMM and 2SLS estimation of mixed regressive, spatial autoregressive models (2007a)
- Spatial Econometrics: From Cross-Sectional Data to Spatial Panels (2014)
- Chapter 36 Large sample estimation and hypothesis testing (1994)
- Generalized Method of Moments, Efficient Bootstrapping, and Improved Inference (2002)
- Hypothesis Testing with Efficient Method of Moments Estimation (1987)
- A Spatial Dynamic Panel Data Model with both Time and Individual Fixed Effects (2010)
- Introduction to Statistical Time Series (1996)
- An Introduction to Multivariate Statistical Analysis (2003)
- Estimating a spatial autoregressive model with an endogenous spatial weight matrix (2015)
- On spatial processes and asymptotic inference under near-epoch dependence (2012)
- Central limit theorems and uniform laws of large numbers for arrays of random fields (2009)
- Panel data models with spatially correlated error components (2007)
- Some recent developments in spatial panel data models (2010)
- On the bootstrap for Moran’s test for spatial dependence (2015)
- Instrumental variable estimation of a spatial dynamic panel model with endogenous spatial weights when T is small (2016)
- QML estimation of spatial dynamic panel data models with endogenous time varying spatial weights matrices (2017)
- Quasi-maximum likelihood estimators for spatial dynamic panel data with fixed effects when both n and T are large (2008)
- QML estimation of dynamic panel data models with spatial errors (2015)
- Using the variance structure of the conditional autoregressive spatial specification to model knowledge spillovers (2008)
- GMM and 2SLS estimation of mixed regressive, spatial autoregressive models (2007)
- A Two-Stage Approach to Spatio-Temporal Analysis with Strong and Weak Cross-Sectional Dependence (2016)
- The spatial and temporal diffusion of house prices in the UK (2011)
- On the Observed-Data Deviance Information Criterion for Volatility Modeling (2016)
- Estimation Methods for Models of Spatial Interaction (1975)
- Simple regression‐based tests for spatial dependence (2011)
- Estimating and Forecasting with a Dynamic Spatial Panel Data Model (2014)
- Spatial econometric Monte Carlo studies: raising the bar (2018)
- The SLX model (2015)
- Matrix Analysis (2013)
- Generalised spatial and spatiotemporal autoregressive conditional heteroscedasticity (2018)
- Spatial and Spatiotemporal GARCH Models – A Unified Approach (2020) — link
- Spatial Autoregressive Conditional Heteroskedasticity Models (2017)
- Estimation and inference for spatial models with heterogeneous coefficients: An application to US house prices (2021)
- Common factors and spatial dependence: an application to US house prices (2021)
- spGARCH: An R-Package for Spatial and Spatiotemporal ARCH and GARCH models (2019)
- Efficient GMM estimation of spatial dynamic panel data models with fixed effects (2014)
- Estimation of spatial autoregressive panel data models with fixed effects (2010)
- A Stationary Spatio-Temporal GARCH Model (2020)
- The spatial spillover effect of local fiscal expenditure in regional housing market: the case of Taiwan (2021)
- Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of United Kingdom Inflation (1982)
- ARCH modeling in finance: A review of the theory and empirical evidence (1992)
- Modelling the persistence of conditional variances (1986)
- Bayesian analysis of stochastic volatility models with fat-tails and correlated errors (2004)
- Partial non- Gaussian state space (1994)
- Bayesian Analysis of Stochastic Volatility Models (1994)
- Estimation of stochastic volatility models via Monte Carlo maximum likelihood (1998)
- Stochastic Volatility: Likelihood Inference and Comparison with ARCH Models (1998)
- Large-sample inference on spatial dependence (2009)
- Spatial extension of generalized autoregressive conditional heteroskedasticity models (2021)
- Bayesian Inference in Spatial Stochastic Volatility Models: An Application to House Price Returns in Chicago (2021)
- A dynamic spatiotemporal stochastic volatility model with an application to environmental risks (2023)
- Dynamic Spatiotemporal ARCH Models (2023)
- Spatial and spatiotemporal volatility models: A review — → 2308.13061
- Changes in the distribution of house prices over time: Structural characteristics, neighborhood, or coefficients? (2008)
- Changes in the distribution of rental prices in Berlin (2015)
- Change in the distribution of house prices across Spanish cities (2012)
- Constructing the Spatial Weights Matrix Using a Local Statistic (2004)
- Socio-economic distance and spatial patterns in unemployment (2002)
- Dual Gravity: Using Spatial Econometrics to Control for Multilateral Resistance (2012)
- Economic Distance and Cross-Country Spillovers (2002)
- Do Local Governments Engage in Strategic Property-Tax Competition? (2001)
- Budget spillovers and fiscal policy interdependence (1993)
- Testing for Strategic Interaction Among Local Governments: The Case of Growth Controls (1998)
- Risk network of global energy markets (2023)
- The role of dispersal in river network metacommunities: Patterns, processes, and pathways (2018)
- Statistical monitoring of European cross-border physical electricity flows using novel temporal edge network processes (2023) — link
- Bayesian Analysis of Spatial Panel Autoregressive Models With Time-Varying Endogenous Spatial Weight Matrices, Common Factors, and Random Coefficients (2016)
- Scenario analysis of livestock-related PM2.5 pollution based on a new heteroskedastic spatiotemporal model (2024)
- Measuring the price of the Arbitrage Pricing Theory (1996)
- Inferential Theory for Factor Models of Large Dimensions (2003)
- Spatial dynamic panel data models with interactive fixed effects (2017)
- Dynamic spatial panel data models with common shocks (2021)
- Time Series Analysis (1994)
- Stochastic volatility with leverage: Fast and efficient likelihood inference (2007)
- Examples of Adaptive MCMC (2009)
- An Adaptive Metropolis Algorithm (2001)
- Observed-data DIC for spatial panel data models (2023)
- Determining the Number of Factors in Approximate Factor Models (2002)
- Determining the number of factors from empirical distribution of eigenvalues (2010)
- Bayesian Measures of Model Complexity and Fit (2002)
- Regression Shrinkage and Selection Via the Lasso (1996)
- The Bayesian Lasso (2008)
- Scale Mixtures of Normal Distributions (1974)
- Penalized regression, standard errors, and Bayesian lassos (2010)
2 of 146 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.