中文摘要：

为解决事故直接经济损失预测困难问题，选用2010--2014年瓦斯事故调查报告的统计数据，对我国瓦斯事故直接经济损失进行建模预测。以直接经济损失作为因变量，死亡人数和事故类型作为解释变量建立回归模型。利用SPSS对模型进行回归，得出事故直接经济损失与死亡人数和类型的关系模型。结果表明瓦斯事故的直接经济损失与死亡人数和事故类型之间存在较强的线性关系。此模型对实际瓦斯事故发生后的直接经济损失做出预测，为制定相应的救援和资金投入计划提供理论支撑。

英文摘要：

In order to predict the direct economic loss in gas accidents in our country, this paper attempted to build a predic- tion model on the basis of the data from 2010 to 2014 survey of gas accident. The regression model was built with direct eco- nomic losses as the dependent variable, and the death toll and accident types as explanatory variables. Using SPSS regres- sion, the relation model of the direct economic loss of accidents and deaths and type was made. The results show that there is a strong linear relationship between the direct economic loss of gas accidents and deaths tolls and accident types. This mod- el, which can predict the direct economic loss of gas accident, provides a theoretical support in formulating appropriate res- cue and funding plan.