12.1 根据下面的数据用excel进行回归,并对回归结果进行讨论,计算 x 1 = 200 , x 2 = 7 x_1=200,x_2=7 x1=200,x2=7时y的预测值。
y |
x 1 x_1 x1 |
x 2 x_2 x2 |
12 |
174 |
3 |
18 |
281 |
9 |
31 |
189 |
4 |
28 |
202 |
8 |
52 |
149 |
9 |
47 |
188 |
12 |
38 |
215 |
5 |
22 |
150 |
11 |
36 |
167 |
8 |
17 |
135 |
5 |
解:
回归统计 |
|
Multiple R |
0.459234179 |
R Square |
0.210896032 |
Adjusted R Square |
-0.014562245 |
标准误差 |
13.34121571 |
观测值 |
10 |
方差分析
|
df |
SS |
MS |
F |
Significance F |
回归分析 |
2 |
332.9837443 |
166.4918721 |
0.935410466 |
0.436485475 |
残差 |
7 |
1245.916256 |
177.9880365 |
|
|
总计 |
9 |
1578.9 |
|
|
|
|
Coefficients |
标准误差 |
t Stat |
P-value |
Lower 95% |
Upper 95% |
下限 95.0% |
上限 95.0% |
Intercept |
25.02870068 |
22.27862726 |
1.123439985 |
0.298297649 |
-27.65188163 |
77.70928299 |
-27.65188163 |
77.70928299 |
x1 |
-0.049714341 |
0.105992426 |
-0.469036735 |
0.653300625 |
-0.300346602 |
0.200917919 |
-0.300346602 |
0.200917919 |
x2 |
1.928169254 |
1.472160474 |
1.309754805 |
0.231623881 |
-1.552937105 |
5.409275613 |
-1.552937105 |
5.409275613 |
回归方程:
y ^ = 25.02870068 − 0.049714341 x 1 + 1.928169254 x 2 \hat{y}=25.02870068-0.049714341x_1+1.928169254x_2 y^=25.02870068−0.049714341x1+1.928169254x2
β ^ 1 = − 0.049714341 \hat{\beta}_1=-0.049714341 β^1=−0.049714341表示在 x 2 x_2 x2不变的条件下, x 1 x_1 x1每变化1个单位,y平均下降0.049714341个单位; β ^ 2 = 1.928169254 \hat{\beta}_2=1.928169254 β^2=1.928169254表示在 x 1 x_1 x1不变的条件下, x 2 x_2 x2每变化1个单位,y平均增加1.928169254个单位。
当 x 1 x_1 x1=200, x 2 = 7 x_2=7 x2=7时,y的预测值为: y ^ = 25.02870068 − 0.049714341 × 200 + 1.928169254 × 7 = 28.58 \hat{y}=25.02870068-0.049714341\times200+1.928169254\times7=28.58 y^=25.02870068−0.049714341×200+1.928169254×7=