Self‐exciting point processes with spatial covariates: modelling the dynamics of crime

Crime has both varying patterns in space, related to features of the environment, economy, and policing, and patterns in time arising from criminal behavior, such as retaliation. Serious crimes may also be presaged by minor crimes of disorder. We demonstrate that these spatial and temporal patterns are generally confounded, requiring analyses to take both into account, and propose a spatio-temporal self-exciting point process model which incorporates spatial features, near-repeat and retaliation effects, and triggering. We develop inference methods and diagnostic tools, such as residual maps, for this model, and through extensive simulation and crime data obtained from Pittsburgh, Pennsylvania, demonstrate its properties and usefulness.

[1]  Shashi Shekhar,et al.  Environmental Criminology , 2008, Encyclopedia of GIS.

[2]  Carter C. Price,et al.  Predictive Policing: The Role of Crime Forecasting in Law Enforcement Operations , 2013 .

[3]  David Vere-Jones.  Probabilities and Information Gain for Earthquake Forecasting , 2013 .

[4]  D. Vere-Jones,et al.  Analyzing earthquake clustering features by using stochastic reconstruction , 2004 .

[5]  M. Tanemura.  Statistical Distributions of Poisson Voronoi Cells in Two and Three Dimensions , 2003 .

[6]  A. Hawkes.  Spectra of some self-exciting and mutually exciting point processes , 1971 .

[7]  Martin A. Andresen,et al.  Crime at Places and Spatial Concentrations: Exploring the Spatial Stability of Property Crime in Vancouver BC, 2003–2013 , 2016, Journal of Quantitative Criminology.

[8]  Bruce G. Taylor,et al.  A randomized controlled trial of different policing strategies at hot spots of violent crime , 2011 .

[9]  S. Galea,et al.  Misdemeanor Policing, Physical Disorder, and Gun-related Homicide: A Spatial Analytic Test of “Broken-Windows” Theory , 2009, Epidemiology.

[10]  Michael Höhle,et al.  A Space–Time Conditional Intensity Model for Invasive Meningococcal Disease Occurrence , 2012, Biometrics.

[11]  George E. Tita,et al.  Measuring and Modeling Repeat and Near-Repeat Burglary Effects , 2009 .

[12]  James J. Heckman,et al.  Identifying the Hand of the Past: Distinguishing State Dependence from Heterogeneity , 1991 .

[13]  Andrea L. Bertozzi,et al.  Randomized Controlled Field Trials of Predictive Policing , 2015 .

[14]  Eric L. Piza,et al.  Risk Clusters, Hotspots, and Spatial Intelligence: Risk Terrain Modeling as an Algorithm for Police Resource Allocation Strategies , 2011 .

[15]  A. Baddeley,et al.  Residual analysis for spatial point processes (with discussion) , 2005 .

[16]  Shane D. Johnson,et al.  Learning where to offend: Effects of past on future burglary locations , 2015 .

[17]  J. Ludwig,et al.  Broken Windows: New Evidence from New York City and a Five-City Social Experiment , 2005 .

[18]  Elizabeth R. Groff,et al.  The Philadelphia Foot Patrol Experiment: A Randomized Controlled Trial of Police Patrol Effectiveness in Violent Crime Hotspots , 2011 .

[19]  Peter Hall,et al.  On Pseudodata Methods for Removing Boundary Effects in Kernel Density Estimation , 1996 .

[20]  J. Hodges,et al.  Adding Spatially-Correlated Errors Can Mess Up the Fixed Effect You Love , 2010 .

[21]  J. Pearl.  Causal inference in statistics: An overview , 2009 .

[22]  Frederic Paik Schoenberg,et al.  Voronoi residual analysis of spatial point process models with applications to California earthquake forecasts , 2014, 1501.06387.

[23]  Anthony A. Braga,et al.  The Effects of Hot Spots Policing on Crime , 2001 .

[24]  Shane D. Johnson.  Repeat burglary victimisation: a tale of two theories , 2008 .

[25]  Y. Ogata.  Seismicity Analysis through Point-process Modeling: A Review , 1999 .

[26]  David M. Hureau,et al.  The Effects of Hot Spots Policing on Crime: An Updated Systematic Review and Meta-Analysis , 2014 .

[27]  Qi Wang,et al.  Standard Errors of Parameter Estimates in the ETAS Model , 2010 .

[28]  Y. Ogata.  The asymptotic behaviour of maximum likelihood estimators for stationary point processes , 1978 .

[29]  Stephen L. Rathbun,et al.  Asymptotic properties of the maximum likelihood estimator for spatio-temporal point processes , 1996 .

[30]  Jerry H. Ratcliffe,et al.  The Predictive Policing Challenges of Near Repeat Armed Street Robberies , 2012 .

[31]  Wilpen L. Gorr,et al.  Forecast accuracy measures for exception reporting using receiver operating characteristic curves , 2009 .

[32]  Matt R. Nobles,et al.  Assessing the Generalizability of the Near Repeat Phenomenon , 2011 .

[33]  David Vere-Jones,et al.  The Entropy Score and its Uses in Earthquake Forecasting , 2005 .

[34]  Spencer Ch.  The Utility of Hotspot Mapping for Predicting Spatial Patterns of Crime , 2008 .

[35]  Isaac T. Van Patten,et al.  A Microspatial Analysis of Robbery: Prospective Hot Spotting in a Small City , 2009 .

[36]  A. Baddeley,et al.  Residual analysis for spatial point processes (with discussion) , 2005 .

[37]  Eric L. Piza,et al.  Vulnerability and Exposure to Crime: Applying Risk Terrain Modeling to the Study of Assault in Chicago , 2016 .

[38]  Wilpen L. Gorr,et al.  Early Warning System for Temporary Crime Hot Spots , 2015 .

[39]  Daryl J. Daley,et al.  An Introduction to the Theory of Point Processes , 2013 .

[40]  M. Townsley,et al.  Infectious Burglaries. A Test of the Near Repeat Hypothesis , 2003 .

[41]  Alex Reinhart,et al.  A Review of Self-Exciting Spatio-Temporal Point Processes and Their Applications , 2017, Statistical Science.

[42]  D. Harte.  Bias in fitting the ETAS model: a case study based on New Zealand seismicity , 2013 .

[43]  A. Veen,et al.  Estimation of Space–Time Branching Process Models in Seismology Using an EM–Type Algorithm , 2006 .

[44]  Frederic Paik Schoenberg,et al.  Facilitated Estimation of ETAS , 2013 .

[45]  Yosihiko Ogata,et al.  Statistical Models for Earthquake Occurrences and Residual Analysis for Point Processes , 1988 .

[46]  George Mohler,et al.  Marked point process hotspot maps for homicide and gun crime prediction in Chicago , 2014 .

[47]  Leonhard Held,et al.  Power-law models for infectious disease spread , 2013, 1308.5115.

[48]  George F. Rengert,et al.  Near-Repeat Patterns in Philadelphia Shootings , 2008 .

[49]  A. Hawkes,et al.  A cluster process representation of a self-exciting process , 1974, Journal of Applied Probability.

[50]  F. Papangelou.  Integrability of expected increments of point processes and a related random change of scale , 1972 .

[51]  A. Raftery,et al.  Strictly Proper Scoring Rules, Prediction, and Estimation , 2007 .

[52]  Wilpen L. Gorr,et al.  Leading Indicators and Spatial Interactions: A Crime‐Forecasting Model for Proactive Police Deployment , 2007 .

[53]  John S. Hollywood,et al.  Evaluation of the Shreveport Predictive Policing Experiment , 2014 .

[54]  Daryl J. Daley,et al.  Scoring probability forecasts for point processes: the entropy score and information gain , 2004, Journal of Applied Probability.

[55]  J. Wilson,et al.  BROKEN WINDOWS: THE POLICE AND NEIGHBOURHOOD SAFETY , 1982 .

[56]  George E. Tita,et al.  Self-Exciting Point Process Modeling of Crime , 2011 .