主成分分析法可消除评价指标之间的相关影响。可减少指标选择的工作量。但是

Principal component analysis can eliminate the correlation between the impact evaluation. You can select targets to reduce the workload. But the results of principal component analysis of the affected dimensionless variables if the respective classes, the result would have been different. The regression analysis does not exist in this case, it is possible to put the standardization of the variables in practice. Then the covariance matrix or correlation matrix analysis.

The main component analysis method eliminates the correlation between evaluation indicators. Reduces the amount of work that indicator selection requires. However, the results of the main component analysis are affected by the volume outline, and if the respective variable syllables, the results will be different. Regression analysis does not exist, so in practice, the data of each variable can be standardized first. Then the covariance matrix or correlation coefficient matrix is used for analysis.

Principal component analysis can eliminate the correlation between evaluation indexes. It can reduce the workload of indicator selection. However, the results of principal component analysis are affected by dimensions. If the variables are different, the results will be different. Regression analysis does not exist in this situation, so in practice, we can first standardize the data of each variable. Then we use covariance matrix or correlation coefficient matrix to analyze.<br>