一般来说，如果未标化预测值（PRE_1）和学生化残差（SRE_1）的散

Generally speaking, if the scatter plots of the unstandardized predicted value (PRE_1) and the studentized residual (SRE_1) are horizontal bands, it means that there is a linear relationship between the dependent variable and all independent variables in multiple linear regression. The results suggest that this study satisfies the assumption that there is a linear relationship between the dependent variable and all independent variables. This figure can also be used to verify equal variance. If equal variance exists, the residuals corresponding to different predicted values ​​should be roughly the same. That is, the points in the figure are evenly distributed, and no special distribution shape appears. If the scatter plot is not evenly distributed, forming a funnel or fan, then the regression will not have equal variance.

In general, if scatterplors that are not marked with predictors (PRE_1) and student residuals (SRE_1) are horizontally banded, there is a linear relationship between the factor variables in multiple linear regressions and all arguments. The results suggest that this study satisfies the hypothesis that there is a linear relationship between the cause variable and all the arguments. By the graph can also 'verify ison variance, if there is ise variance, the residuals corresponding to different predicted values should be about the same. That is, the points in the figure are evenly distributed and no special distribution shapes appear. If scatterpouts are unevenly distributed to form funnels or fan shapes, regression does not have equal variance.

In general, if the pre is not standardized_ 1) And student residuals (SRE)_ 1) The scatter plot of is horizontal band, which shows that there is a linear relationship between dependent variables and all independent variables in multiple linear regression. The results indicate that this study satisfies the hypothesis that there is a linear relationship between dependent variables and all independent variables. If there is equivariance, the residuals corresponding to different predicted values should be roughly the same. That is to say, each point in the graph is evenly distributed, and no special distribution shape will appear. If the scatter plot is unevenly distributed, forming a funnel or sector, then the regression does not have the equal variance.<br>