标题: 如何使用SPSS或SAS求解满意度研究中的结构方程? [打印本页] 作者: shiyiming 时间: 2004-7-21 10:20 标题: 如何使用SPSS或SAS求解满意度研究中的结构方程? 我想这可能是调研中用的最复杂的统计学技术啦,先攻这个难关,剩下的就小菜一碟啦 <!-- s:D --><img src="{SMILIES_PATH}/icon_biggrin.gif" alt=":D" title="Very Happy" /><!-- s:D -->作者: shiyiming 时间: 2004-7-21 14:39 标题: re In sas, proc calis can handle it.
SPSS can not run sem model ,but Amos can.作者: shiyiming 时间: 2004-7-22 09:49 标题: 3x liuchaos
thanks for you answer though I know that.would you mind giving me some samples or detail instruction please?作者: shiyiming 时间: 2004-7-27 14:56 标题: re You can browse this site to gain many detailed sample program: <!-- m --><a class="postlink" href="http://www.ats.ucla.edu/stat/sas/library/proc_calis.htm">http://www.ats.ucla.edu/stat/sas/library/proc_calis.htm</a><!-- m -->
In fact, it is difficult to say what kind of detailed instructions can be helpful, you should adjust the initial model many many times to get a sound model.
I think the sas online documents can tell you what you want,moreove, the specific theory background (how you draw the initial path diagram)and market experience also play a very important role when building a good model.作者: shiyiming 时间: 2004-8-5 22:55 标题: 关于满意度中的最小二乘估计的潜变量结构方程模型 关于这个问题,用一般的SAS和SPSS都不能很好的解决,SPSS的AMOS可以用来做MLE估计的协方差结构方程模型,但是与解决满意度的潜变量结构方程模型不相同,SAS的结构方程模型解决的是一般问题,与AMOS的大致相同,但解决用最小二乘估计的潜变量结构方程模型要用专门的算法,我们已经开发出了这样的软件。现在很多人都在误用最小二乘估计的潜变量结构方程模型来解决满意度问题,这是可悲之处。