论文部分内容阅读
目的运用GM、SPSS、SAS、EXCEL等软件建立我国出生缺陷发生率的灰色预测模型、回归模型、ARIMA模型,比较模型的优缺点并选择最优模型预测未来几年出生缺陷的变化,为母婴保健工作提供科学的依据。方法查找《中国卫生统计年鉴》2002-2011年出生缺陷发生率,用GM软件拟合GM(1,1)模型,用SPSS拟合回归模型,用SAS拟合ARIMA模型。结果灰色模型为y(t)=5 961.7e~(0.0218(t-1))-5 849.58,残差平方和为119.83;回归模型为Y=0.091X×3-2.103X×2+17.4X+97.928,残差平方和64.43;该序列为白噪声序列无法建立ARIMA模型。结论回归模型的精确度更高。对未来几年的出生缺陷进行预测,我国的出生缺陷发生率总体呈上升趋势,相关部门应积极采取干预措施降低发生率。
Objective To establish the gray prediction model, regression model and ARIMA model of the incidence of birth defects in China by using software such as GM, SPSS, SAS and EXCEL, to compare the advantages and disadvantages of the models and to select the optimal model to predict the changes of birth defects in the coming years. Health work to provide a scientific basis. Methods The incidence of birth defects in China Health Statistical Yearbook 2002 to 2011 was searched. The GM (1,1) model was fitted with GM software, the regression model was fitted with SPSS, and the ARIMA model was fitted with SAS. The results showed that the gray model was y (t) = 5 961.7e ~ (0.0218 (t-1)) - 5 849.58 and the residual sum of squares was 119.83. The regression model was Y = 0.091X × 3-2.103X × 2 + 17.4X + 97.928, residual sum of squares 64.43; ARIMA model can not be established for this sequence as white noise sequence. Conclusion The regression model is more accurate. Predict birth defects in the next few years, the incidence of birth defects in our country is generally on the rise, and relevant departments should actively take interventions to reduce the incidence.