标题: SAS 是否合适做穷举法？ [打印本页] 作者: shiyiming 时间: 2010-3-24 20:19 标题: SAS 是否合适做穷举法？ 现在要做一个有虚拟变量的多元线性回归模型，要用到穷举法，找的r-square最大的。有人说SAS不适合做穷举法，不知道是不是真的？如果SAS可以做，应该使用什么样的语句，请各位高人给个主意。
小弟非常感谢大家！！！！！ <!-- s:D --><img src="{SMILIES_PATH}/icon_biggrin.gif" alt=":D" title="Very Happy" /><!-- s:D --> <!-- s:D --><img src="{SMILIES_PATH}/icon_biggrin.gif" alt=":D" title="Very Happy" /><!-- s:D --> <!-- s:D --><img src="{SMILIES_PATH}/icon_biggrin.gif" alt=":D" title="Very Happy" /><!-- s:D -->作者: shiyiming 时间: 2010-3-26 07:58 标题: Re: SAS 是否合适做穷举法？ If the model selection procedure itself is of no interest in your research, it might as well take what the software provides instead by our own. In PROC REG, it gives a variety of methods on model selection, including selection by largest r square. I am not sure if that will meet with the need. I believe that those methods should be more than only ‘穷举法‘。If we do the model selection by our own, it is very tedious and way time-consuming.作者: shiyiming 时间: 2010-3-27 21:04 标题: Re: SAS 是否合适做穷举法？ MSR
STEPWISE