【摘 要】
：
Past studies have shown that crime behaviors are clustered.This study investigates the data of violence or robbery related to crimes in the city of Castellon,Spain,during 2012 and 2013.We consider usi
【机 构】
：
Institute of Statistical Mathematics,Tokyo 1908562,Japan
论文部分内容阅读
Past studies have shown that crime behaviors are clustered.This study investigates the data of violence or robbery related to crimes in the city of Castellon,Spain,during 2012 and 2013.We consider using the following space-time point-process model to describe the data,which is completely specified by a conditional intensity function λ(t,x,y)= μt(t)μd(t)μw(t)μb(x,y)+∫t-∞∫∫Sg(t-s,x-u,y-v)N(du dv ds),(1)where μt(t),μd(t),and μw(t)represent the trend term,the daily periodicity,the weekly periodicity in the temporal components of the background rate,μb(x,y)represent the spatial homogeneity of the background rate,respectively,and g(t-s,x-u,y-v)represents the subprocess triggered by an event previously occurring at location(u,v)and time s.A nonparametric method,called stochastic reconstruction,is used to estimate each component,including daily and weekly periodicities of background rate,spatial background rate,long-term background trend,and the spatial and temporal response function in the triggering component,of the conditional intensity of the model.The results show that the background rate of the occurrence process of violence or robbery related to crimes in the city of Castellon,Spain,during 2012 and 2013,includes clear daily and weekly periodicity.The reconstructed spatial and temporal response functions in the clustering component imply that,once a crime occurs,it likely trigger another crime within the coming 3 days and within 100 meters in distance.The parameter estimates are μ0 = 0.771 and A = 0,029.
其他文献
Monitoring sea levels at a local level is vital for protecting coastal populations,ecological systems,and natural resources.
A clinical trial,adaptive design that allows pre-specified modifications in the design or statistical procedures of the trial depending on accrued data makes a trial more flexible.
We consider an infinite dimensional generalization of natural exponential family of probability densities,which are parametrized by functions in a reproducing kernel Hilbert space(RKHS),and show it to
In recent years there has been an increased interest in statistical analysis of data with multiple types of relations among a set of entities.
N-of-1 trials are single-patient multiple-crossover studies for determining the relative effectiveness of treatments for an individual participant.
Beyond the obvious use of large scale RCT data to establish a treatment effect the same data can be used to understand/document modes-of-operation for the treatment or identify additional patient rele
The Current Population Survey(CPS)is a monthly household sample survey consisting of eight rotation groups,so that each selected household will be interviewed for 4 consecutive months and another 4 co
This paper considers the statistical inferences of current status failure time data arising from a proportional hazards model with varying coefficients.
We develop a functional conditional autoregressive(CAR)model for spatially correlated data for which functions are collected on areal units of a lattice.
Varying-coefficient models have been widely used to investigate the possible time-dependent effects of covariates when the response variable comes from normal distribution.