数据分析.docx

1、数据分析解：(1)拟合与的线性回归模型 利用与的观测数据，通过SAS系统prog reg 过程拟合线性回归模型 拟合出的拟合值，残差及学生化残差程序:建立回归模型,输出因变量拟合值、残差、学生化残差data exercise2_9;input x1-x3 y;cards; 50 51 2.3 48 36 46 2.3 57 40 48 2.2 66 41 44 1.8 70 28 43 1.8 89 49 54 2.9 36 42 50 2.2 46 45 48 2.4 54 52 62 2.9 26 29 50 2.1 77 29 48 2.4 89 43 53 2.4 67 38 55 2

2、.2 47 34 51 2.3 51 53 54 2.2 57 36 49 2.0 66 33 56 2.5 79 29 46 1.9 88 33 49 2.1 60 55 51 2.4 49 29 52 2.3 77 44 58 2.9 52 43 50 2.3 60 ;run;proc reg data=exercise2_9;model y=x1-x3;output out=a p=precdit r=resid student=student;proc print data=a;run; The SAS System 18:26 Sunday, October 10, 2004 1 T

3、he REG Procedure Model: MODEL1 Dependent Variable: y Analysis of Variance Sum of MeanSource DF Squares Square F Value Pr FModel 3 4133.63322 1377.87774 13.01 |t|Intercept 1 162.87590 25.77565 6.32 |r| under H0: Rho=0 R Q R 1.00000 0.98357 .0001 Q 0.98357 1.00000 Fx1 1.000000 0.5986 31.31 FModel 1 36

4、78.43585 3678.43585 31.31 FIntercept 121.83182 11.04221 14299 121.73 .0001x1 -1.52704 0.27288 3678.43585 31.31 Fx2 0.782276 0.6641 3.90 0.0622x3 0.752300 0.6613 3.70 0.0686 Variable x2 Entered: R-Square = 0.6641 and C(p) = 2.4951 Analysis of Variance Sum of MeanSource DF Squares Square F Value Pr FM

5、odel 2 4081.21949 2040.60975 19.77 FIntercept 166.59133 24.90844 4616.26752 44.73 Fx1 0.3190 0.3451 19.00 0.0003x2 0.0655 0.5986 3.90 0.0622 Statistics for Entry DF = 1,19 ModelVariable Tolerance R-Square F Value Pr Fx3 0.348121 0.6727 0.50 0.4902All variables left in the model are significant at th

6、e 0.1000 level.No other variable met the 0.1000 significance level for entry into the model. Summary of Stepwise Selection Variable Variable Number Partial ModelStep Entered Removed Vars In R-Square R-Square C(p) F Value Pr F1 x1 1 0.5986 0.5986 4.2995 31.31 FModel 2 4081.21949 2040.60975 19.77 |t|Intercept 1 166.59133 24.90844 6.69 .0001x1 1 -1.26046 0.28919 -4.36 0.0003x2 1 -1.08932 0.55139 -1.98 0.0622复相关系数平方和为与前面的结果0.6727相比较，可见均方残差、回归系数估计及拟合优度的度量值均变化很小，即当在模型中时，对的影响是很小的最优回