A Scalable MCEM Estimator for Spatio-Temporal Autoregressive Models

Very large spatio-temporal lattice data are becoming increasingly common across a variety of disciplines. However, estimating interdependence across space and time in large areal datasets remains challenging, as existing approaches are often (i) not scalable, (ii) designed for conditionally Gaussian outcome data, or (iii) are limited to cross-sectional and univariate outcomes. This paper proposes an MCEM estimation strategy for a family of latent-Gaussian multivariate spatio-temporal models that addresses these issues. The proposed estimator is applicable to a wide range of non-Gaussian outcomes, and implementations for binary and count outcomes are discussed explicitly. The methodology is illustrated on simulated data, as well as on weekly data of IS-related events in Syrian districts.

[1]  Philip A. Schrodt Precedents, Progress, and Prospects in Political Event Data , 2012 .

[2]  James P. LeSage,et al.  Fast Simulated Maximum Likelihood Estimation of the Spatial Probit Model Capable of Handling Large Samples , 2011 .

[3]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[4]  S. Glaser,et al.  A review of spatial econometric models for count data , 2017 .

[5]  Thomas H. Klier,et al.  Clustering of Auto Supplier Plants in the United States , 2008 .

[6]  Y. Ye,et al.  Interior Algorithms for Linear, Quadratic, and Linearly Constrained Convex Programming , 1997 .

[7]  R. Pace,et al.  Sparse spatial autoregressions , 1997 .

[8]  David S. Siroky,et al.  A Comparison of the Small-Sample Properties of Several Estimators for Spatial-Lag Count Models , 2009 .

[9]  Virgilio Gómez-Rubio,et al.  Spatial Point Patterns: Methodology and Applications with R , 2016 .

[10]  K. Gleditsch,et al.  It’s the Local Economy, Stupid! Geographic Wealth Dispersion and Conflict Outbreak Location , 2011 .

[11]  S. Kalyvas,et al.  The logic of violence in civil war , 2011 .

[12]  D. McMillen PROBIT WITH SPATIAL AUTOCORRELATION , 1992 .

[13]  W. Gilks,et al.  Adaptive rejection sampling from log-concave density functions , 1993 .

[14]  Luc Anselin,et al.  An O(N) parallel method of computing the Log-Jacobian of the variable transformation for models with spatial interaction on a lattice , 2009, Comput. Stat. Data Anal..

[15]  Andreas Forø Tollefsen,et al.  PRIO-GRID: A unified spatial data structure , 2012 .

[16]  Roger Bivand,et al.  Computing the Jacobian in Gaussian Spatial Autoregressive Models: An Illustrated Comparison of Available Methods , 2013 .

[17]  Florian M. Hollenbach,et al.  Technology and Collective Action: The Effect of Cell Phone Coverage on Political Violence in Africa , 2013, American Political Science Review.

[18]  Efficient High-Dimensional Importance Sampling in Mixture Frameworks , 2011 .

[19]  D. Lambert,et al.  A two-step estimator for a spatial lag model of counts: Theory, small sample performance and an application☆ , 2010 .

[20]  Jeffrey M. Wooldridge,et al.  Partial maximum likelihood estimation of spatial probit models , 2013 .

[21]  Clionadh Raleigh,et al.  Introducing ACLED: An Armed Conflict Location and Event Dataset , 2010 .

[22]  Maciej Dakowicz A unified spatial data structure for GIS , 2009 .

[23]  Luc Anselin,et al.  Thirty years of spatial econometrics , 2010 .

[24]  Raffaella Calabrese,et al.  Estimators of Binary Spatial Autoregressive Models: A Monte Carlo Study , 2013, 1302.3414.

[25]  T. Louis Finding the Observed Information Matrix When Using the EM Algorithm , 1982 .

[26]  Jude C. Hays,et al.  Spatial- and Spatiotemporal-Autoregressive Probit Models of Interdependent Binary Outcomes* , 2015, Political Science Research and Methods.

[27]  Roman Liesenfeld,et al.  Likelihood Based Inference and Prediction in Spatio-Temporal Panel Count Models for Urban Crimes , 2015 .

[28]  Nils B. Weidmann,et al.  Predicting Conflict in Space and Time , 2010 .

[29]  Wim P. M. Vijverberg,et al.  Probit in a Spatial Context: A Monte Carlo Analysis , 2004 .

[30]  Rajesh Paleti,et al.  A Spatial Multivariate Count Model for Firm Location Decisions , 2014 .

[31]  J. LeSage Introduction to spatial econometrics , 2009 .

[32]  Evgenia K. Akritas,et al.  Various proofs of Sylvester's (determinant) identity , 1996 .

[33]  Avinash S. Bhati,et al.  A Generalized Cross-Entropy Approach for Modeling Spatially Correlated Counts , 2008 .

[34]  J. LeSage Bayesian Estimation of Limited Dependent Variable Spatial Autoregressive Models , 2010 .

[35]  Joris Pinkse,et al.  Contracting in space: An application of spatial statistics to discrete-choice models , 1998 .

[36]  A. Tollefsen Insurgency and Inaccessibility 1 , 2015 .

[37]  K. Ord Estimation Methods for Models of Spatial Interaction , 1975 .

[38]  C. McCulloch,et al.  A Monte Carlo EM method for estimating multinomial probit models , 2000 .

[39]  Galin L. Jones,et al.  Ascent‐based Monte Carlo expectation– maximization , 2005 .

[40]  Jean-Francois Richard,et al.  Likelihood Evaluation of High-Dimensional Spatial Latent Gaussian Models with Non-Gaussian Response Variables , 2015 .