http://down.cenet.org.cn/view.asp?id=78686

https://bbs.pinggu.org/b86i288716.html

[此贴子已经被作者于2008-8-28 11:00:29编辑过]

可不可以再说的具体点儿呢！？不胜感激！

The following is copied from stata web, I think it may be helpful and achieve your goal although there is no direct way to quantile panel data. Usually the best method is in your heart.

I'm not sure about the theory underlying how the sampling variance is estimated with qreg, but as far as I know, the only way to deal with clustering in your data within the context of quantile regression, is to bootstrap. Besides the bs command you can also look into clad (Censored Least Absolute Deviations estimator with bootstrapped se).

One way to deal with clustering, I believe, is to bootstrap your standard
errors using the cluster option (for info, just type "help bs").

> Dear All,
>
> for my thesis, I would like to estimate the returns to education for
> immigrants
> and natives at different points in the earnings distribution. I have a
> large
> panel data set with 85000 observations. I want to make use of quantile
> regression techniques; however, I am not sure if this works with
> longitudinal data.
>
> Is anyone of you aware of panel data features for quantile regression? Or
> is
> there anything like the cluster-option for quantile regression in order to

> take
> account of the dependence among individuals?

http://down.cenet.org.cn/view.asp?id=78686

https://bbs.pinggu.org/b86i288716.html

[此贴子已经被作者于2008-8-28 11:02:06编辑过]

谢谢！非常感谢！