Data decentralization of SPSS regression analysis

1. Centralization is to subtract the mean and Z-score is to divide it by the standard deviation. Both of them are centralization methods.

2. Standardize the data, find out the mean and variance
analysis description statistics description, and then select "save standardized score as a variable" and confirm to get the processed standardized data, and then cluster, factor and regression analysis can be carried out

3. Correlation analysis uses raw data

4. Why watch it? After data centralization, the mean value should be 0 and the standard deviation should be 1

analysis -- descriptive
statistics --- descriptive

5. Jingdong express can generally arrive the next day, depending on whether there is a delay on the road caused by weather.

6. It will take at least two days on the road, and the time limit may be extended ring the festival
the transit transportation between other provinces of Jingdong is slower than that of SF express, so it is the slow delivery of Jingdong.

7. Because double 11 Jingdong express pressure mountain, a large number of express hoarding, resulting in no timely delivery! My express has been there for two days, but it hasn't been moved. It's estimated that I have to wait for a day or so. I have already consulted the customer service of Jingdong by phone, and they also answered me like this!

8. 371 = cobalt blue helmet 372 = cobalt blue heavy helmet 373 = cobalt blue mask 374 = cobalt blue breastplate 375 = cobalt blue leg armor 376 = mitag hood 377 = mitag heavy helmet 378 = mitag helmet 379 = mitag Chain Armor 380 = mitag Shin armor 684 = frost helmet 685 = frost breastplate 686 = frost Shin armor 687 = tin helmet 688 = tin Shin armor 689 = tin Shin armor 690 = lead helmet 691 = lead Shin armor 692 = lead Shin armor 693 = tungsten helmet 694 = tungsten Shin armor 695 = tungsten Shin armor 696 =Platinum helmet 697 = platinum chain armor 698 = platinum shin guard 727 = wood helmet 728 = wood shin guard 729 = wood shin guard 730 = ebony helmet 731 = ebony shin guard 732 = ebony shin guard 733 = Solid Mahogany helmet 734 = Solid Mahogany shin guard 735 = Solid Mahogany shin guard 736 = pearl wood helmet 737 = Pearl wood shin guard 738 = pearl wood shin guard

9. First of all, let's explain that each symbol, B, that is beta, represents the regression coefficient, and the standardized regression coefficient represents the correlation between the independent variable, that is, the prediction variable and the dependent variable. Why should we standardize? Because when we standardize, the units of the independent variable and the dependent variable can be unified to make the results more accurate and rece the errors caused by different units. T value is the result of t-test for regression coefficient. The larger the absolute value is, the smaller the sig is. Sig represents the significance of t-test; 0.05 is generally considered to be significant in coefficient test, which means that the absolute value of your regression coefficient is significantly greater than 0, indicating that the independent variable can effectively predict the variation of the dependent variable. To make this conclusion, you may make a mistake in 5%, that is, 95% of you are sure that the conclusion is correct
for regression test, first of all, look at the ANOVA table, that is, F test. That table represents a general test for the regression coefficients of all the independent variables that you regress. If sig & lt; This indicates that at least one independent variable can effectively predict the dependent variable. When writing the data analysis results, it is generally not necessary to report
then look at the coefficient table to see whether the standardized regression coefficient is significant. Each independent variable has a corresponding regression coefficient and significance test
finally, look at the model summary table, and R is called the coefficient of determination, It is the proportion of the variation that can be explained by the independent variable to the total variation of the dependent variable, which represents the degree of explanation of the regression equation to the dependent variable. When reporting, report the adjusted R-square. This value is a correction to the fact that the increase of the independent variable will continuously enhance the predictive power (because even if there is no useful independent variable, as long as you add a few more, the R-square will become larger, The adjusted R is a punishment for many independent variables, and R can be ignored. In the case of standardization, R is also a correlation between independent variables and dependent variables
I hope it is useful for you