predicted R2 与adjusted R2的问题

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

The predicted R2 of 0.8823 was in reasonable agreement with the adjusted R2 of 0.9641,
which had advocated a high correlation between the observed values
and the predicted values. This means that the regression model
provides an excellent explanation of the relationship between the
independent variables (factors) and the response (selectivity).这句话怎么理解

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：Predicted adjusted predict adjust just adjusted Predicted

musashino2008 发表于 2010-10-2 19:55
The predicted R2 of 0.8823 was in reasonable agreement with the adjusted R2 of 0.9641,
which had advocated a high correlation between the observed values
and the predicted values. This means that the regression model
provides an excellent explanation of the relationship between the
independent variables (factors) and the response (selectivity).这句话怎么理解

The adjusted R2 should be less than R2.

当自变量越来越多时，残差的平方和会越来越小，也就是SSR会越来越小，SSE会越来越大，又R^2=SSE/SST，所以增加自变量的数目就可以使R^2变大，但这并不是回归方程解释力增强了，可能一堆自变量、且有很高R^2的回归方程，但其实没有任何用处，adjusted R^2去除了自变量数目的影响，可以更准确地评估回归方程的解释力

楼上正解。但SSR与SSE搞反了。即当自变量越来越多时，残差的平方和会越来越小，也就是SSE会越来越小，SSR会越来越大，又R^2=SSR/SST
呵呵。。。

SSR是不是组间误差平方和呀？有叫SSM的，各种叫法不统一呀