If I use the ZOOM in PDF to look at the loess curve, the curve is very wiggly, so I am a little suspect about this use of the loess method. Other than the wigglyness, the curves of KR are almost right on top of the loess curves.
Also, The link for the simulation code (reference 29) does not work. I'd also like to see a link for the Kernel regression method.
Weird Loess + bad link
9 November 2006
If I use the ZOOM in PDF to look at the loess curve, the curve is very wiggly, so I am a little suspect about this use of the loess method. Other than the wigglyness, the curves of KR are almost right on top of the loess curves.
Also, The link for the simulation code (reference 29) does not work. I'd also like to see a link for the Kernel regression method.
Competing interests
None declared