请高手帮忙看看这是怎么回事(关于logistic模型)

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

本人建了一个logistic模型，用的方法是向前逐步回归condition，但是这个结果我就看不懂了，是这四个变量都进入了模型了吗，那为什么后几个变量的sig.值这么大啊（没通过检验）。请高手帮我分系一下原因，万分感谢！！！！

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏0 回帖

关键词：Logistic模型 logistic logisti ogistic logist 模型

也感觉很奇怪啊，貌似没有一个变量是有意义的，可怎么都留在方程里了呢？用向前逐步回归的LR试试，比较一下看看。

]LR方法也试了，结果差不多
Variables in the Equation
                 B        S.E.        Wald        df        Sig.        Exp(B)
Step 1        X81(1)        5.637        1.147        24.159        1        .000        280.500
        Constant        -1.705        .544        9.836        1        .002        .182
Step 2        X81(1)        6.310        1.251        25.434        1        .000        550.000
        X125(1)        -22.775        18799.972        .000        1        .999        .000
        Constant        20.377        18799.972        .000        1        .999        707520407.543
Step 3        X4        .000        .000        3.880        1        .049        1.000
        X81(1)        7.748        1.784        18.865        1        .000        2316.425
        X125(1)        -23.661        19085.606        .000        1        .999        .000
        Constant        18.569        19085.606        .000        1        .999        115980272.149
Step 4        X4        .000        .000        3.773        1        .052        1.000
        X81(1)        24.484        5483.352        .000        1        .996        42973672114.624
        X9(1)        -19.729        5483.352        .000        1        .997        .000
        X125(1)        -23.284        19105.216        .000        1        .999        .000
        Constant        18.710        19105.216        .000        1        .999        133582443.942
a        Variable(s) entered on step 1: X81.
b        Variable(s) entered on step 2: X125.
c        Variable(s) entered on step 3: X4.
d        Variable(s) entered on step 4: X9.

Huge S.E  indicates your have serious problems in your analysis. Post your whole results output to see what's going on.

附件是完整结果，请高手指点一二！
Logistic Regression完整结果.doc (412.5 KB)

2011-1-10 22:21:31 上传

拜托了！！

我也遇到了这样的问题，期待高手解答~

Had a quick look at your whole results. The following are my thoughts for your reference.

1. You have a small sample size (78) and a lot of predictors (x1 to x127). This is not good for logistic regresion. Based on your response (dependent) variable (0: 23 observations, 1: 55 observations), theoretically you'd better  not put more than 3 predictors in your logistic model .
Based on your data, maybe loglinear model is a better choice.
If you really like to use logistic regression, pay attention to the following issues:
1. First please make sure all your questions follow the same directions (for example, 1 indicates positive, 0 indicates negative).
2. Do a univariate analysis by dependent variable, based on this, select 3-4 variables, put them in your logistic
model (just used forced entry or enter, not stepwise)
3. When you run logistic analysis, select correlation matrix.
4. In the correlatin matrix, if two variables are highly correlated (r>0.9), delete one of them, then re-run the model.
5. In your final model, the "S.E" should be very small

Good luck with your analysis

thank you!thank you!

8# hplcdadong 受教了 谢谢