请问stata做多层线性（三层）如何做？

如题……请高手指教……
数据为截面数据

pkujinxin 发表于 2012-8-10 19:36
谢谢，你说的xtmixed是不是只能针对面板数据呢，我的数据是截面，可以吗……
我刚刚 help xtmixed，
说 ...

我刚刚打错了是xtmixed，垂直分层模型(HLM)和多层回归模型(Multilevel)是一个意思。

xtmix

夸克之一 发表于 2012-8-10 18:30
xtmix

谢谢，你说的xtmixed是不是只能针对面板数据呢，我的数据是截面，可以吗……
我刚刚 help xtmixed，
说明用来分析Multilevel mixed-effects linear regression
这个模型和hierarchical linear modeling是一回事儿吗……

夸克之一 发表于 2012-8-10 18:30
xtmix

我看到了，可以用截面数据，非常感谢哈

我看到论坛有问类似问题的帖子，也有高手给出的答案用xtmixed
但我们共同的困惑都是这个命令是不是可以用在截面数据中，下面这段表述可以用来回答了：
    xtmixed fits linear mixed models.  Mixed models are characterized as containing both fixed effects and random effects.  The fixed effects are analogous to standard regression
    coefficients and are estimated directly.  The random effects are not directly estimated but are summarized according to their estimated variances and covariances.  Although random
    effects are not directly estimated, you can form best linear unbiased predictions (BLUPs) of them (and standard errors) by using predict after xtmixed; see [XT] xtmixed
    postestimation.  Random effects may take the form of either random intercepts or random coefficients, and the grouping structure of the data may consist of multiple levels of nested
    groups.  As such, mixed models are also known in the literature as multilevel models and hierarchical linear models. The overall error distribution of the linear mixed model is
    assumed to be Gaussian, and heteroskedasticity and correlations within lowest-level groups also may be modeled.

楼主做出来了吗？

楼主数据量大么？我的数据量大的时候似乎stata无效啊。。。跑不出来结果。。。。一直显示在运算中