首先运用主成分分析方法对北京市经济指标数据进行降维处理,然后基于降维后的数据拟合部分线性模型.将拟合后的模型对2008年北京市税收进行预测,所得结果优于常用的逐步线性回归分析方法的预测结果.
The paper first reduces the dimension of the economic data of Beijing by principal component analysis method.Then based on the dimension-reduced data,a partial linear model is applied in forecast the revenue of Beijing in 2008.The results show a great advantage over those by stepwise linear regression analysis.