分位数回归

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

Dependent Variable: LNY
Method: Quantile Regression (tau = 0.9)
Date: 06/24/13   Time: 09:29
Sample: 1981 2011
Included observations: 31
Huber Sandwich Standard Errors & Covariance
Sparsity method: Kernel (Epanechnikov) using residuals
Bandwidth method: Hall-Sheather, bw=0.11014
Estimation successfully identifies unique optimal solution
Bandwith too large in sandwich covariance estimation
Error in sandwich covariance estimation
Variable					Coefficient	Std. Error		t-Statistic	Prob.
LNX1					0.756215	NA		NA	NA
LNX2					0.149467	NA		NA	NA
LNX6					-0.589655	NA		NA	NA
LNX8					-0.518195	NA		NA	NA
Pseudo R-squared					0.615232	Mean dependent var			4.651394
Adjusted R-squared					0.572480	S.D. dependent var			0.255578
S.E. of regression					0.133434	Objective			0.422381
Quantile dependent var					4.951864	Objective (const. only)			1.097753

做分位数回归，选择0.9 出现上面这种情况，0.1的时候也是这样  0.15和0.85的时候是正常的，请问各位这是什么原因，正常的吗？

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：分位数回归 分位数 observations Successfully coefficients method 2011