GLS vs. OLS [推广有奖]

0关注
0粉丝

已卖：65份资源

硕士生

21%

还不是VIP/贵宾

威望: 0 级
论坛币: 481 个
通用积分: 0
学术水平: 0 点
热心指数: 0 点
信用等级: 0 点
经验: 531 点
帖子: 85
精华: 0
在线时间: 125 小时
注册时间: 2009-6-22
最后登录: 2021-7-8

楼主

chicagobox123 发表于 2009-8-28 22:50:04 |AI写论文

是否 +2 论坛币

k人参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

GLS (generalized least square)
OLS (ordinary least square)

OLS要求residual 没有autocorrelaiton，GLS可以处理，我想找几个实际的例子，上课用，谢谢。

扫码加我拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏0 回帖

关键词：OLS Generalized Generalize Ordinary autocorr OLS GLS

回帖推荐

chnlj 发表于2楼查看完整内容

Even if the error is serially correlatd, you can still use OLS as long as you use the serial-correlation-robust standard error (such as Newey-West standard errors). For time series data, there are many examples with serially correlated errors. How about change of consumption = coefficient*change of income + error

本帖被以下文库推荐

· 计量.统计精彩问答|主题: 12506, 订阅: 52

沙发

chnlj 发表于 2009-9-9 02:43:51

Even if the error is serially correlatd, you can still use OLS as long as you use the serial-correlation-robust standard error (such as Newey-West standard errors).

For time series data, there are many examples with serially correlated errors.
How about
change of consumption = coefficient*change of income + error