Frank Harrell wrote:
[...]
Thank you Brian. It seems that no matter what is the right answer, the
answer currently returned on my system is clearly wrong. lowess()$y
should be constrained to be within range(y).
Really? That assertion is offered without proof and I am pretty sure is
Prof Brian Ripley wrote:
Frank Harrell wrote:
[...]
Thank you Brian. It seems that no matter what is the right answer, the
answer currently returned on my system is clearly wrong. lowess()$y
should be constrained to be within range(y).
Really? That assertion is offered without proof
PROTECTED] On Behalf Of Frank E Harrell Jr
Sent: Friday, October 13, 2006 5:51 AM
To: Prof Brian Ripley
Cc: [EMAIL PROTECTED]
Subject: Re: [R] Bug in lowess
Prof Brian Ripley wrote:
Frank Harrell wrote:
[...]
Thank you Brian. It seems that no matter what is the right answer, the
answer
On Wed, 2006-10-11 at 22:29 -0500, Frank E Harrell Jr wrote:
x - c(0,7,8,14,15,120,242)
y - c(122,128,130,158,110,110,92)
lowess(x,y)
$x
[1] 0 7 8 14 15 120 242
$y
[1] 122. 128. 132.2857 158. 110. -4930.
110.
Same behaviour here on a more
Prof Brian Ripley wrote:
On Thu, 12 Oct 2006, Gavin Simpson wrote:
On Wed, 2006-10-11 at 22:29 -0500, Frank E Harrell Jr wrote:
x - c(0,7,8,14,15,120,242)
y - c(122,128,130,158,110,110,92)
lowess(x,y)
$x
[1] 0 7 8 14 15 120 242
$y
[1] 122. 128. 132.2857
x - c(0,7,8,14,15,120,242)
y - c(122,128,130,158,110,110,92)
lowess(x,y)
$x
[1] 0 7 8 14 15 120 242
$y
[1] 122. 128. 132.2857 158. 110. -4930.
110.
R version 2.2.1, 2005-12-20, i486-pc-linux-gnu
attached base packages:
[1] methods stats