logistic回归出现问题，请大师指教

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

横截面Logistic回归，显示出现下面的提示，请问各位大师，这是哪里出问题了？
proc logistic data=shuju.sample2;
model div(event="1")=oconf cps growth size leverage state nprps year2010 year2011 year2012 v1-v11;
run;

NOTE: PROC LOGISTIC is modeling the probability that div=1.
WARNING: There is possibly a quasi-complete separation of data points. The maximum likelihood estimate may not exist.
WARNING: The LOGISTIC procedure continues in spite of the above warning. Results shown are based on the last maximum
         likelihood iteration. Validity of the model fit is questionable.

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回归 logistic logisti ogistic logist procedure possibly warning growth points

Quasi-complete separation in a logistic/probit regression happens when the outcome variable separates a predictor variable or a combination of predictor .
有很多解决办法。去看看
Allison, Convergence Failures in Logistic Regression, SAS Global Forum 2008

yuerqieqie 发表于 2014-4-4 22:08
Quasi-complete separation in a logistic/probit regression happens when the outcome variable separate ...

请问下，logit回归和logistic回归在sas中有没有区别，还是一样的，命令有区别吗？

xiezhibin 发表于 2014-4-4 22:15
请问下，logit回归和logistic回归在sas中有没有区别，还是一样的，命令有区别吗？

在SAS应该都可以用PROC LOGISTIC。话说在概念上这两个有区别么？