A factor analysis of the socio-economic structure of riot and crime prone cities

The major purpose of this paper is to investigate whether individual attacks against property and the recent urban riots, which researchers also agree were property oriented, arise out of a similar set of socio-economic conditions. The paper proceeds by first briefly reviewing the theoretical and empirical literature on the causes of crime and collective violence. This literature is then drawn upon to construct 24 independent variables which are measures of income, employment and educational opportunities, population characteristics and socio-political conditions. The statistical analysis in the second part of the paper employed a sample of 129 large Standard Metropolitan Statistical Areas, 64 of which experienced one or more incidents of racial violence between 1965 and 1968 and 65 of which were nonriot SMSA's. From the 24 variables, seven factors were extracted by the minimum residual method and orthogonally rotated by the Kaiser varimax technique. These seven factors were then used as independent variables in both regression and discriminate analysis in which riot intensity (measured by property and economic loss) and property crime rates were used as independent variables. The paper concludes that criminal behavior derives from fundamentally different causes than does riot activity.     

THE PREDICTIVE PERFORMANCE OF THREE AUTOREGRESSIVE MOVING-AVERAGE MODELS:A MONTE CARLO INVESTIGATION

Abstract. The relative accuracy of point and interval forecasts from three related autoregressive moving-average (ARMA) models—multivariate, univariate, and transfer function—is evaluated in this study. It is found that the multivariate models produce the most accurate one- and three-step-ahead point forecasts of nonindependent series. However, the most accurate point forecasts of independent series are generated by the univariate models. Compared with the multivariate models, the transfer function predictions are relatively unreliable, but with the appropriate restrictions they are superior to the univariate forecasts in certain cases. Interval forecasts from the correctly specified models are reliable indicators of forecast dispersion.