[讨论]STATA 专题讨论

一般线性模型是不是就指线性回归？或者说是广义线性模型的特殊形式?

不知道用什么命令做这个。是用regress还是GLM？

在SPSS里面general linear model, generalized linear model,regress这几个命令都有，有些不明白

这是statalist里面的一段话，请教高手

I can't say what you need.

Historically the abbreviation -glim- (or more
precisely GLIM) was used for software implementing
generalized l.m.s (sensu Nelder and Wedderburn).

My guess is that -glm- was used in Stata as a
slightly different name precisely to avoid any
inference (implication, too) that -glm- matched
GLIM one-to-one, which it certainly did not.

But if Joe Hilbe is watching he can beat guessing
and tell us why he chose that name.

Nick
n.j.cox@durham.ac.uk

Ricardo Ovaldia

 
> Thank you Nick. I new that generalized linear models
> were not what I need it. Using the acronym "GLM" for
> both general and generalized is very confusing. I
> think that maybe -mvreg- is what I really need.

 
Nick Cox

 
> > Usually, -regress- or -glm-, except that
> > neither captures absolutely all the
> > functionality that some authors associate
> > with GLM. Note that general linear models
> > and generalised linear models are not
> > the same families.

 
Ricardo Ovaldia

> > > What command can I use to fit a General linear
> > Model in Stata?

我想问一个问题，我需要用unbalanced panel-data 做two equations 的回归，找了很久找到似乎是用到xtsur 这个命令，但是我在回归的时候，总是报错，出来的是

estimates post: matrix has missing values

这是什么原因啊？

非常感谢

以下是引用jiuzhuo在2008-9-29 15:19:00的发言：

我想问一个问题，我需要用unbalanced panel-data 做two equations 的回归，找了很久找到似乎是用到xtsur 这个命令，但是我在回归的时候，总是报错，出来的是

estimates post: matrix has missing values

这是什么原因啊？

非常感谢

SUR model 要求 T>N , 不知你的数据是何种类型，变量中是否存在缺漏值？

谢谢！

我的数据只有3年,2个等式。

其中有些解释变量是time-invariant的

有缺漏值吧

那要怎么处理呢？

关于paneldata里面提到的检验序列相关、异方差等命令，如xttest1 xttest2 和xttest3在Stata10.0里面无法实现啊？

findit xttest1

findit xttest2

……

的确是好东西，谢谢了

Wonderful! It will help to use the Stata!

能免费下载，谢谢楼主了！！！

Stata确实是一个好东西