【摘要】 [目的]了解汶川地震后灾区儿童创伤后应激障碍(PTSD)现状,并分析其影响因素。[方法]按照分层随机抽样方法的原则抽取253例调查对象,通过Bootstrap再抽样方法扩大样本量至2000例,在对资料进行描述性分析的基础上,通过SAS Enterprise Miner软件和决策树C4.5算法建立决策树模型,分析儿童患PTSD的影响因素。[结果]对儿童是否患PTSD建立决策树模型,其对训练集,验证集,测试集有分类错误率分别为0.070,0.100,0.075,按重要性排序筛选出汶川地震后影响灾区儿童患PTSD的7个影响因素。[结论]决策树C4.5算法建立的模型效果较好。针对地震后灾区儿童患PTSD的主要影响因素,采取相应的措施,有助于降低儿童患PTSD的比例。更多还原

【Abstract】 [Objective] To understand the posttraumatic stress disorder (PTSD) status among children after wenchuan earthquake and analyze its influencing factors. [Methods] Data were collected through stratified and random sampling. The sample size that 253 cases was increased to 2000 cases through Bootstrap resample. On the basis of the descriptive analysis of the data, a decision tree model was built up with SAS software and decision tree of C4.5 to analyze the influencing factors of PTSD among children. [Results] The misclassification of the training set, the valid set and the test set of the decision tree was 5.30%, 8.00%, 6.50%, respectively. The study found that the top seven factors affecting the PTSD. [Conclusion] The goodness of fit for the model of decision tree of C4.5 is satisfactory. For the main factors of PTSD among the children after earthquake, taking appropriate measures is effective to reduce the proportion of PTSD among children effectively.更多还原