作者candypinky (飞~)
看板Statistics
标题[问题] OLS 与 GLS
时间Thu May 14 12:15:08 2009
我有个问题一直困扰很久，就是OLS跟GLS的差别在哪里呢？我是知道当用OLS估计的结果
如果不具效率的话要改用GLS啦，但除此之外，有没有分线性模型只能用OLS估计，非线
性模型要用GLS这样的分别呢？
--
※ 发信站: 批踢踢实业坊(ptt.cc)
◆ From: 118.169.230.211
1F：推 PinkQQ: simply put, one could apply GLS while the problem of 07/07 13:55
2F：→ PinkQQ: heteoskedastic errors occur, so that we want to find 07/07 13:55
3F：→ PinkQQ: a nonsingular and squared matrix to transform the data 07/07 13:56
4F：→ PinkQQ: However, GLS is often unable to applied because we do 07/07 13:56
5F：→ PinkQQ: not know what Var(y) is (so does the transformed M). 07/07 13:57
6F：→ PinkQQ: Hence, we use FGLS instead. But another problem is 07/07 13:57
7F：→ PinkQQ: that FGLS often doesn't have the nice properties in 07/07 13:58
8F：→ PinkQQ: finite sample and could be a less efficient estimator 07/07 13:58
9F：→ PinkQQ: than OLS. 07/07 13:58