Prof. Ripley,
thank you for being more explicit now! Thank you also for the fix to
the wish that you derived from my bug report. Here comes the rationale
for my updated patch, which I *humbly* propose as a more general
solution to the problem.
I have spent several days now on this problem, but I
Dear R Developers,
Prediction intervals for weighted regression are treated in
Brown, P. J. (1994) Measurement, Regression and Calibration. Oxford
on p. 35. However, the prediction interval for Z is not really
spelled out in a way that would be accessible for me.
So I give up on this.
Dear R developers,
I am a little disappointed that my bug report only made it to the
wishlist, with the argument:
Well, it does not say it has.
Only relevant to prediction intervals.
predict.lm does calculate prediction intervals for linear models from
weighted regression, so th
Full_Name: Johannes Ranke
Version: 2.3.0
OS: Linux-i386
Submission from: (NULL) (134.102.60.74)
In the case that predict.lm is used on an object resulting from weighted linear
regression with interval="prediction", the prediction intervals currently depend
on
the absolute size of object$weights:
