作者chrisjon (恬静悠闲)
看板Statistics
标题[问题] 回归题目意思
时间Sat Nov 17 14:41:33 2007
Yi = β0 + β1X1 + β2X2 +εi
︿
Yi = -0.24 - 0.036*X1 + 0.132*X2
Yi = Net Income
X1 = Sales
X2 = Assets
(d)
At the .05 level of significance, determine whether each independent variable
makes a contribution to the regression model.
Based on these results, indicate the regression model that should be
utilized in this problem.
(e)
Evalute the appropriateness of the developed model.
d看不太懂,不过根据e小题,感觉应该是要检定出β1或β2不显着,但是两者都显着
再看了一下β0,却是不显着的
难道d是要检定出β0=0,然後e小题要把原模型改成0截距模型吗?
怕会错题目意思,上来请教一下
--
要常玩BG
头脑才不会退化
--
※ 发信站: 批踢踢实业坊(ptt.cc)
◆ From: 163.25.135.136
1F:推 dick0631:d应该是检定H_0:beta_1=beta_2=0 =>应该会reject H_0 11/17 16:10
2F:→ dick0631:接着再个别检定beta_1=0和beta_2=0,将没有reject H_0的 11/17 16:11
3F:→ dick0631:解释变数剔除掉。变成reduce form. 11/17 16:11
4F:推 chrisjon:SPSS报表的显着性β0:0.984 ; β1:0.018 ; β2:0.000 11/17 16:20
5F:→ chrisjon:在α=0.05条件下,我们拒绝了β0,那我们改reduce成零截 11/17 16:22
6F:→ chrisjon:距模型? 我这样说对吗? 11/17 16:22
7F:推 chrisjon:谢了!因为用无截距模型很不习惯,所以问一下^^" 11/17 16:30
8F:推 dick0631:这是题目,就照题目的意思做。实际上,检定beta_0是比较 11/17 17:25
9F:→ dick0631:没有意义的。 11/17 17:26