Displaying 2 results from an estimated 2 matches for "lm_lm".
Did you mean:
m_lm
2000 Apr 25
0
Wrong SEs in predict.lm(..., type="terms")
...ding checks against S-PLUS, have extended to fitting
spline curves. I have not tested the code with any example where
the pivot sequence does not run sequentially from 1 to p1.
For what it is worth, I am using RW-1.0.0 under Windows 98.
df<-data.frame(x=1:9,y=c(2,3,6,4,8,10,12,14,15))
> df.lm_lm(y~x,data=df)
> as.vector(predict(df.lm,se=T,type="terms")$se.fit)
[1] 0.9904885 0.7428664 0.4952442 0.2476221 0.0000000 0.2476221 0.4952442
[8] 0.7428664 0.9904885
Here is what one should get:
> abs((df$x-mean(df$x)))*summary(df.lm)$coef[2,2]
[1] 0.5769836 0.4327377 0.2884918 0.144...
2000 Apr 26
0
Wrong SEs in predict.lm(..., type="terms") (PR#528)
...to begin with the minimum necessary changes.
My tests, including checks against S-PLUS, have extended to fitting
spline curves. I have not tested the code with any example where
the pivot sequence does not run sequentially from 1 to p1.
df<-data.frame(x=1:9,y=c(2,3,6,4,8,10,12,14,15))
> df.lm_lm(y~x,data=df)
> as.vector(predict(df.lm,se=T,type="terms")$se.fit)
[1] 0.9904885 0.7428664 0.4952442 0.2476221 0.0000000 0.2476221 0.4952442
[8] 0.7428664 0.9904885
Here is what one should get:
> abs((df$x-mean(df$x)))*summary(df.lm)$coef[2,2]
[1] 0.5769836 0.4327377 0.2884918 0.144...