一类相关性指标优化IOWHA组合模型的预测比较

Prediction Comparison of a Class of Correlation Index Optimized IOWHA Combination Models

文章以民航客运量为研究对象,采集1996—2016年民航客运量及核心影响要素的相关数据,在多元线性回归和ARIMA预测模型的基础上,引入相关性指标,分别构建基于相关系数、夹角余弦和灰色关联度的IOWHA组合模型,结果显示:基于相关系数、向量夹角余弦和灰色关联度的IOWHA组合模型的误差明显优于多元回归和ARIMA(1,2,1),证实了相关性指标优化IOWHA组合预测模型的有效性与合理性。

Taking civil aviation passenger volume as the research object,this paperfirstcollects relevant data of civil aviation passenger volume and core influencing factors from 1996 to 2016. And then, on the basis of multiple linear regression and ARIMA prediction model, the paper introduces correlation index and constructs IOWHA combination model based on correlation coefficient, the included angle cosine and the grey correlation degree respectively. The results show that the error of the IOWHA combination model based on the correlation coefficient, the cosine of the angle between vectors and the grey correlation degree is significantly better than that of the multiple regression and ARIMA(1,2,1), verifying the validity and rationality of the IOWHA combination prediction model optimized by correlation index.