Space-Time Autoregressive Models and Forecasting National, Regional and State Crime Rates
29 Pages Posted: 2 May 2014
Date Written: 2012
Abstract
The recently advanced space-time-autoregressive (ST-AR) model is used to forecast U.S., regional and state violent and property crime rates. The disaggregate state (Florida) violent crime model includes murder, rape, robbery, and assault and the property crime model, burglary, larceny, and motor vehicle theft. In experimental forecasts, ST-AR RMSEs are compared to those for aggregate univariate AR(p) models, vector autoregression (VAR), Bayesian VAR (BVAR), and two naïve models that predict future crime rates as either the most recent rate or according to the most recent change in rates. The ST-AR model is of particular interest, given its efficient use of data, much like panel-data estimation. The ST-AR, BVAR, and AR(p) models outperform the other three approaches, but the ST-AR models are generally superior.
Keywords: Crime forecasting, Autoregressive models, Disaggregation, Regional forecasting, Time-series
JEL Classification: K42, C22, R15
Suggested Citation: Suggested Citation