Citation

Liu Y, Hu XM, Chen Y, Fu ZW. Zhonghua Liu Xing Bing Xue Za Zhi 2018; 39(5): 664-668.

Affiliation

Office of Endemic and Chronic Disease Control, Department of Trophical and Non-communicable Disease Control and Prevention, Hainan Provincial Center for Disease Control and Prevention, Haikou 570203, China.

Copyright

(Copyright © 2018, Zhonghua yi xue hui)

DOI

10.3760/cma.j.issn.0254-6450.2018.05.024

PMID

29860814

Abstract

Objective: To analyze the trend of suicide mortality in residents of Hainan province, and explore the application of time sequence model in the prediction of the mortality of suicide. Methods: The mortality data of suicide in residents of Hainan province between January, 2014 and December, 2016 were collected and analyzed with time sequence model and the mortality rate of suicide during January-June, 2017 in Hainan was predicted with the model. Results: During January, 2014 to June 2017, a total of 576 suicide cases were reported in Hainan, the mortality rate was 1.5/100 000. The established ARIMA model had good fitting for the suicide mortality in previous times and the prediction result was quite similar to the actual mortality, the predicted mortality rate was within the 95% confidence interval of the actual rate. Conclusion: The time sequence model for the prediction of suicide mortality in Hainan was "ARIMA (0, 1, 0) (0, 0, 0) (12)" , and the prediction effect of the model was better, which can be used to predict the suicide mortality in Hainan.

Language: zh

Vernacular Abstract

目的： 分析海南省居民自杀报告死亡率变化趋势，探索时间序列模型在自杀死亡率预测中的应用。

方法：

应用时间序列模型拟合海南省2014年1月至2016年12月自杀死亡率资料，并预测该地区2017年1－6月的自杀死亡率。
结果：
海南省2014年1月至2017年6月该地区报告自杀死亡576人，平均死亡率为1.5/10万；所建立的ARIMA模型较好地拟合了既往时间序列的自杀死亡率，预测值的动态趋势与实际值基本一致，2017年1－6月的实际值均在预测值95%的可信区间范围内。

结论：

确定海南省自杀死亡率的时间序列模型为"ARIMA（0，1，0）（0，0，0）(12)"，且模型的预测效果较好，可以用来预测海南省因自杀导致的死亡情况。.

Language: zh

Keywords

Injury; Suicide; Time sequence