Paper: arXiv 2511.01271
Authors: Zhaoxing Gao, Sihan Tu, Ruey S. Tsay
Abstract
This paper investigates estimation and inference of a Spatial Arbitrage Pricing Theory (SAPT) model that integrates spatial interactions with multi-factor analysis, accommodating both observable and latent factors. Building on the classical mean-variance analysis, we introduce a class of Spatial Capital Asset Pricing Models (SCAPM) that account for spatial effects in high-dimensional assets, where we define {"\it spatial rho"} as a counterpart to market beta in CAPM. We then extend SCAPM to a general SAPT framework under a {"\it complete"} market setting by incorporating multiple factors. For SAPT with observable factors, we propose a generalized shrinkage Yule-Walker (SYW) estimation method that integrates ridge regression to estimate spatial and factor coefficients. When factors are latent, we first apply an autocovariance-based eigenanalysis to extract factors, then employ the SYW method using the estimated factors. We establish asymptotic properties for these estimators under high-dimensional settings where both the dimension and sample size diverge. Finally, we use simulated and real data examples to demonstrate the efficacy and usefulness of the proposed model and method.
Complexity vs Empirical Score
- Math Complexity: 9.2/10
- Empirical Rigor: 6.8/10
- Quadrant: Holy Grail — high math complexity, high empirical rigor
Why this score: The paper introduces highly advanced mathematical techniques including ridge-regularized Yule-Walker equations, eigenanalysis for latent factor extraction, and establishes asymptotic properties under high-dimensional settings where both dimension and sample size diverge, indicating very high mathematical complexity. The empirical rigor is substantial due to the inclusion of both simulated and real data examples, demonstration of efficacy, and discussion of implementation challenges, though it lacks the explicit code or backtest metrics that would push it toward maximum rigor.
Research Flowchart
flowchart TD
A["Research Goal<br>Estimate & Infer SAPT Model<br>in High-Dimensions"] --> B{"Factor Type?"}
B --> C["Observable Factors"]
B --> D["Latent Factors"]
C --> E["SYW Estimation<br>Ridge Regression"]
D --> F["Autocovariance Eigenanalysis<br>Extract Factors"]
F --> E
E --> G["Key Outcomes<br>Generalized Shrinkage Yule-Walker<br>Asymptotic Properties<br>Spatial Rho Metric"]
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 Spatial Arbitrage Pricing Theory (SAPT) model with spatial rho and a generalized shrinkage Yule‑Walker estimation method for observable and latent factors.
Source sentence
This paper introduced a Spatial Arbitrage Pricing Theory (SAPT) model that integrates spatial interactions with multifactor structures involving both observable and latent variables.
Assumes 6
- The process {(yt, ft)} is strictly stationary and α‑mixing with a summable mixing coefficient. statistical
Source sentence
Assumption 1. The process {(yt, ft)} is strictly stationary and α-mixing with the mixing coefficient satisfying the condition
- The spatial weight matrix W is known, has zero diagonal, and SN(ρ) is invertible with bounded row/column sums. model
Source sentence
Assumption 2. The spatial weight matrix W is known with zero main diagonal elements, and the matrix SN(ρ) := IN −D(ρ)W is invertible. The row and column sums of |W| and |SN(ρ)−1| are bounded uniformly in N.
- The error term {εt} is white noise and uncorrelated with past yt and ft. statistical
Source sentence
Assumption 3. {εt} is a white noise process satisfying Cov(yt−j, εt) = 0 and Cov(ft−k, εt) = 0, for j ≥1 and k ≥0, respectively.
- If factors are observed, loading matrix B elements are uniformly bounded; if latent, B is full rank satisfying a normalization. model
Source sentence
Assumption 4. (i) If ft’s are observed, each element in B are bounded uniformly in N; (ii) If ft’s
Show 2 more
- The market is complete, allowing linear combinations of assets to replicate any asset return. market
Source sentence
Definition 1 (Complete Market). Suppose there are N risky assets in the market, where N is sufficiently large. The market is said to be complete if the return of any asset r…
- Moment conditions: E|fj,t|2γ and E|εk,t|2γ are bounded. statistical
Source sentence
Assumption 5. For 1 ≤j ≤K and 1 ≤k ≤N, E|fj,t|2γ < C and E|εk,t|2γ < C, where γ is given in Assumption 1.
Data
- S&P 500 constituents daily log excess returns market-prices public
Source sentence
Our analysis focuses on the daily log excess returns of S&P 500 constituents from January 2004 to December 2016, comprising 3,273 time points across 205 companies.
Costs
Not applicable
Finds 2
- The proposed SAPT method outperforms QMLE and the classical Fama‑French factor model in out‑of‑sample forecasting. performance
Source sentence
out-of-sample forecasting performance compared to QMLE and the classical Fama-French factor model
- Simulation results show the approach outperforms alternatives in out‑of‑sample forecasting. performance
Source sentence
The results show that our approach outperforms these alternatives in out-of-sample forecasting.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 15 related papers). Coverage is partial, so this is neither replication nor refutation.
1 paper in the archive
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 (142)
- Improving estimation of portfolio risk using new statistical factors — → 2409.17182
- Joint estimation and inference for multi-experiment networks of high-dimensional point processes (2021) — link
- Supervised dynamic pca: Linear dynamic forecasting with many predictors — → 2307.07689
- Divide-and-conquer: a distributed hierarchical factor approach to modeling large-scale time series data (2023)
- Arbitrage pricing with heterogeneous spatial effects and heteroscedastic disturbances (2023)
- Estimation and model selection in general spatial dynamic panel data models (2020)
- Common factors and spatial dependence: An application to US house prices (2021)
- Dynamic spatial panel data models with common shocks (2021)
and 134 more
- Large panels with common factors and spatial correlation (2011)
- Multidimensional statistical scatter (1960)
- Applied multivariate analysis: using Bayesian and frequentist methods of inference (2005)
- Momentum and autocorrelation in stock returns (2002)
- Large sample properties of generalized method of moments estimators (1982)
- Risk measurement when shares are subject to infrequent trading (1979)
- Friction in the trading process and the estimation of systematic risk (1983)
- Betas and their regression tendencies (1975)
- A simple model of non-stationarity of systematic risk (1977)
- The Econometrics of Financial Markets (1997)
- Endogeneity bias in beta estimation: Thailand and Hong Kong (1994)
- Asset pricing: Revised edition (2009)
- Capital asset prices: A theory of market equilibrium under conditions of risk (1964)
- Portfolio selection (1952)
- A structural-factor approach to modeling high-dimensional time series and space-time data (2019)
- GMM estimation of spatial autoregressive models with unknown heteroskedasticity (2010)
- Quasi-maximum likelihood estimators for spatial dynamic panel data with fixed effects when both n and T are large (2008)
- Banded spatio-temporal autoregressions (2019)
- Asset pricing with spatial interaction (2018)
- Does corporate headquarters location matter for stock returns? (2006)
- Some recent developments in spatial panel data models (2010)
- Spatial autocorrelation. (1973)
- Statistics for spatial data (2015)
- Spatial econometrics: methods and models (1988)
- Common risk factors in the returns on stocks and bonds (1993)
- The rank of demand systems: theory and nonparametric estimation (1991)
- Common and country-specific fluctuations in productivity, investment, and the current account (1999)
- Nonlinear time series: nonparametric and parametric methods (2003)
- Modeling high-dimensional time series: A factor model with dynamically dependent factors and diverging eigenvalues (2022)
- Principal components estimation and identification of static factors (2013)
- Generalized dynamic principal components (2016)
- Factor models in high-dimensional time series—a time-domain approach (2013)
- The generalized dynamic factor model: one-sided estimation and forecasting (2005)
- The generalized dynamic-factor model: Identification and estimation (2000)
- Estimation of latent factors for high-dimensional time series (2011)
- Factor modeling for high-dimensional time series: inference for the number of factors (2012)
- Asymptotic distributions of quasi-maximum likelihood estimators for spatial autoregressive models (2004)
- Budget spillovers and fiscal policy interdependence: Evidence from the states (1993)
- Minimax sparse principal subspace estimation in high dimensions (2013)
- High-dimensional probability: An introduction with applications in data science (2018)
- A Two-Way Transformed Factor Model for Matrix-Variate Time Series (2021)
- Truncated power method for sparse eigenvalue problems (2013)
- Deflation methods for sparse PCA (2008)
- Expectation-maximization for sparse and non-negative PCA (2008)
- Sparse principal component analysis (2006)
- Divide-and-conquer: a distributed hierarchical factor approach to modeling large-scale time series data (2022)
- Estimating Latent Asset Pricing Factors (2020)
- Large Dimensional Latent Factor Modeling with Missing Observations and Applications to Causal Inference (2020)
- Interpretable Sparse Proximate Factors for Large Dimensions (2020)
- A five-factor asset pricing model (2015)
- On the systematic and idiosyncratic volatility with large panel high-frequency data (2018)
- On the number of common factors with high-frequency data (2017)
- Testing against constant factor loading matrix with large panel high-frequency data (2018)
- Identification and estimation of a large factor model with structural instability (2017)
- Estimation of large dimensional factor models with an unknown number of breaks (2018)
- Estimating and testing high dimensional factor models with multiple structural changes (2020)
- Simultaneous multiple change-point and factor analysis for high-dimensional time series (2018)
- Estimation and inference of change points in high-dimensional factor models (2020)
- Lecture notes on nonparametrics (2009)
- Automatic lag selection in covariance matrix estimation (1994)
- Measuring uncertainty (2015)
- Principal component analysis of high-frequency data (2019)
- Asymptotic properties of a robust variance matrix estimator for panel data when T is large (2007)
- Confidence intervals for diffusion index forecasts and inference with factor-augmented regressions (2006)
- Using principal component analysis to estimate a high dimensional factor model with high-frequency data (2017)
- Nonparametric Estimation of Large Covariance Matrices with Conditional Sparsity (2019)
- Projected principal component analysis in factor models (2016)
- A factor analysis of bond risk premia (2009)
- Large covariance estimation by thresholding principal orthogonal complements (2013)
- Fitting dynamic factor models to non-stationary time series (2011)
- An introduction to multivariate statistical analysis (1958)
- Three likelihood-based methods for mean and covariance structure analysis with nonnormal missing data (2000)
- Inference in Group Factor Models with an Application to Mixed Frequency Data (2019)
- Matrix theory (2012)
- Matrix perturbation theory (1990)
- Matrix differential calculus (1988)
- Factors that Fit the Time-Series and Cross-Section of Stock Returns (2020)
- Understanding Systematic Risk: A High-Frequency Approach (2020)
- Large-Dimensional Factor Modeling Based on High-Frequency Observations (2019)
- Modeling bond yields in finance and macroeconomics (2005)
- Determining the number of factors in approximate factor models (2002)
- Determining the number of factors from empirical distribution of eigenvalues (2010)
- Pooling of forecasts (2002)
- Dynamic Factor Models (2011)
- Large dimensional factor analysis (2008)
- Inferential theory for factor models of large dimensions (2003)
- Testing for structural breaks in dynamic factor models (2011)
- Economic forecasting: some lessons from recent research (2003)
- Forecasting Using Principal Components From a Large Number of Predictors (2002)
- Identification and estimation of a large factor model with structural instability (2017)
- On time-varying factor models: Estimation and testing (2017)
- Decomposing the yield curve (2009)
- A Test for the Number of Factors in an Approximate Factor Model (1993)
- Dynamic Factor Models with Time-Varying Parameters: Measuring Changes in International Business Cycles (2008)
- Local stationary factor models: identification and nonparametric estimation (2017)
- Modelling methodology and forecast failure (2002)
- Detecting big structural breaks in large factor models (2014)
- Tests for parameter instability in dynamic factor models (2015)
- Forecasting in dynamic factor models subject to structural instability (2009)
- Measuring the Effects of Monetary Policy: A Factor-Augmented Vector Autoregressive (FAVAR) Approach (2004)
- Implications of Dynamic Factor Models for VAR Analysis (2005)
- Shrinkage estimation of high-dimensional factor models with structural instabilities (2016)
- Arbitrage, factor structure, and mean-variance analysis on large asset markets (1983)
- Eigenvalue ratio test for the number of factors (2013)
- Testing for structural breaks in dynamic factor models (2011)
- Forecasting in the Presence of Structural Breaks and Policy Regime Shifts (2005)
- Modeling methodology and forecast failure (2002)
- Consistent factor estimation in dynamic factor models with structural instability (2013)
- Tests for Parameter Instability and Structural Change with Unknown Change Point (1993)
- Dynamic Factor Models: A Review of the Literature (2013)
- The arbitrage theory of capital asset pricing (1976)
- Inferential theory for factor models of large dimensions (2003)
- Macroeconomic Forecasting Using Diffusion Indexes (2002)
- Forecasting the term structure of government bond yields (2006)
- Testing for factor loading structural change under common breaks (2015)
- Classical time varying factor-augmented vector auto-regressive models-estimation, forecasting and structural analysis (2015)
- Performance measurement with the arbitrage pricing theory (1986)
- Maximum Likelihood Estimation of Time-Varying Loadings in High-Dimensional Factor Models (2015)
- Nonparametric Estimation of Time-Varying Parameters (1989)
- Macroeconomic Forecasting Using Diffusion Indexes (2002)
- Forecasting non-stationary economic time series (2001)
- Bond risk premia (2005)
- Time Series Modelling With Semiparametric Factor Dynamics (2009)
- A generalized moments estimator for the autoregressive parameter in a spatial model (1999)
- Estimation and inference for spatial models with heterogeneous coefficients: an application to US house prices (2021)
- Fixed-effects dynamic spatial panel data models and impulse response analysis (2017)
- Consistent estimates based on partially consistent observations (1948)
- Generalized Yule–Walker estimation for spatio-temporal models with unknown diagonal coefficients (2016)
- Understanding systematic risk: A high-frequency approach (2020)
- Specification and estimation of spatial autoregressive models with autoregressive and heteroskedastic disturbances (2010)
- Test assets and weak factors (2025)
- Taming the factor zoo: A test of new factors (2020)
- Regularized LIML for many instruments (2015)
- Adaptive GMM shrinkage estimation with consistent moment selection (2013)
2 of 142 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.