作者vivienne2246 (vivienne)
看板Statistics
标题[程式] R 跑lqs回归,如何找出各系数是否显着
时间Thu Jan 28 20:25:43 2010
------------------------------------------------------------------------
[软体程式类别]:
R
[程式问题]:
回归
[软体熟悉度]:
新手(不到1个)
[问题叙述]:
使用package为MASS的lqs(x,...,method = c("lms"))
为什麽输入summary(),所跑出来的结果无法看到Std. Error, T value, Pr(>|t|)
, R-squared...等资料呢?
如果想要的到那些数据该如何给指令呢?
[程式范例]:
> library(MASS)
> mylqs <- lqs(Ration1 ~ Ration2+ Ration3 , data=mydata, method=c("lms"))
> mylqs
Call:
lqs.formula(formula = Ration1 ~ Ration2+ Ration3, data = mydata,
method = c("lms"))
Coefficients:
(Intercept) Ration2 Ration3
0.625 0.500 0.250
Scale estimates 0.5093 0.6519
这里的两个Scale estimates分别代表什麽呢?
> summary(mylqs)
Length Class Mode
crit 1 -none- numeric
sing 1 -none- character
coefficients 3 -none- numeric
bestone 3 -none- numeric
fitted.values 13 -none- numeric
residuals 13 -none- numeric
scale 2 -none- numeric
terms 3 terms call
call 4 -none- call
xlevels 0 -none- list
model 3 data.frame list
如何才能知道每个估计系数的P值呢?
-----------------------------------------------------------------------------
--
※ 发信站: 批踢踢实业坊(ptt.cc)
◆ From: 140.123.162.105