我有截距项回归的拟合优度不到百分45,共三步回归,如下
Stepwise Selection: Step 1
Variable x1 Entered: R-Square = 0.4067 and C(p) = 6.6063
Analysis of Variance
Sum of Mean
Source DF Squares Square F Value Pr > F
Model 1 0.42030 0.42030 34.28 <.0001
Error 50 0.61313 0.01226
Corrected Total 51 1.03343
Parameter Standard
Variable Estimate Error Type II SS F Value Pr > F
Intercept 4.09725 1.47741 0.09431 7.69 0.0078
x1 0.87776 0.14993 0.42030 34.28 <.0001
Stepwise Selection: Step 2
Variable x2 Entered: R-Square = 0.4485 and C(p) = 4.7594
Analysis of Variance
Sum of Mean
Source DF Squares Square F Value Pr > F
Model 2 0.46350 0.23175 19.92 <.0001
Error 49 0.56994 0.01163
Corrected Total 51 1.03343
Parameter Standard
Variable Estimate Error Type II SS F Value Pr > F
Intercept 1.24167 2.06548 0.00420 0.36 0.5505
x1 0.98079 0.15550 0.46273 39.78 <.0001
x2 0.06717 0.03486 0.04319 3.71 0.0598
Bounds on condition number: 1.1341, 4.5364
--------------------------------------------------------------------------------------------
Stepwise Selection: Step 3
Variable x2 Removed: R-Square = 0.4067 and C(p) = 6.6063
Sum of Mean
Source DF Squares Square F Value Pr > F
Model 1 0.42030 0.42030 34.28 <.0001
Error 50 0.61313 0.01226
Corrected Total 51 1.03343
Parameter Standard
Variable Estimate Error Type II SS F Value Pr > F
Intercept 4.09725 1.47741 0.09431 7.69 0.0078
x1 0.87776 0.14993 0.42030 34.28 <.0001
但是去掉截距回归拟合优度达到百分99.999999999.我觉得不靠谱呀。如下
Variable x1 Entered: R-Square = 0.9999 and C(p) = 12.3743
NOTE: No intercept in model. R-Square is redefined.
Analysis of Variance
Sum of Mean
Source DF Squares Square F Value Pr > F
Model 1 8448.63991 8448.63991 609068 <.0001
Error 51 0.70744 0.01387
Uncorrected Total 52 8449.34736
希望指点。不胜感激。