Correlates of homicide: new space/time interaction tests for spatiotemporal point processes
Correlates of homicide: new space/time interaction tests for spatiotemporal point processes
复制标题
凶杀案的相关性：时空点过程的新时空相互作用测试
DOI：
10.1184/r1/6471155.v1
复制
发表时间：
2013
影响因子：
1.9
通讯作者：
Alex Smola
中科院分区：
文献类型：
--
作者：
S. Flaxman;Daniel B. Neill;Alex Smola
对时空数据的统计推断通常通过关注数据的时间方面而忽略空间或空间方面而忽略时间来进行。在本文中，我们明确地集中在空间和时间之间的相互作用。使用一个地理编码，时间戳数据集从芝加哥近900万个电话911在2007年和2010年之间，我们问这些呼叫类型是否与枪击或凶杀案。标准的相关技术在时空环境中不会产生有意义的结果，因为有两个混淆：纯粹的空间效应（即“坏”社区）和纯粹的时间效应（即夏季更多的犯罪）可能会引入虚假的相关性。为了解决这个问题，已经提出了一些时空相互作用的统计测试，明确控制可分离的空间和时间依赖性。然而，这些经典测试都有局限性。我们提出了一个新的测试时空相互作用，使用美世基于核的统计量测量概率分布之间的距离。我们将我们的新测试与现有的模拟和真实的数据测试进行比较，它的性能优于或优于经典测试。对于我们考虑的应用程序，我们发现911呼叫类型和枪击/凶杀案之间存在许多有趣且重要的时空相互作用。
Statistical inference on spatiotemporal data often proceeds by focusing on the temporal aspect of the data, ignoring space, or the spatial aspect, ignoring time. In this paper, we explicitly focus on the interaction between space and time. Using a geocoded, time-stamped dataset from Chicago of almost 9 millions calls to 911 between 2007 and 2010, we ask whether any of these call types are associated with shootings or homicides. Standard correlation techniques do not produce meaningful results in the spatiotemporal setting because of two confounds: purely spatial e ff ects (i.e. “bad” neighborhoods) and purely temporal e ff ects (i.e. more crimes in the summer) could introduce spurious correlations. To address this issue, a handful of statistical tests for space-time interaction have been proposed, which explicitly control for separable spatial and temporal dependencies. Yet these classical tests each have limitations. We propose a new test for space-time interaction, using a Mercer kernel-based statistic for measuring the distance between probability distributions. We compare our new test to existing tests on simulated and real data, where it performs comparably to or better than the classical tests. For the application we consider, we find a number of interesting and significant space-time interactions between 911 call types and shootings / homicides.
多元非齐次时空泊松过程的非参数贝叶斯分割。
影响因子：
4.4
作者：
Ding,Mingtao;He,Lihan;Dunson,David;Carin,Lawrence
通讯作者：
Carin,Lawrence