Thankyou very much Joachim. Actually I already know the residual() command. I
only wanted to know that is there a way to account for the fitted lines? its
more of a criosity rather than a problem.
:)
Thankyou very much once again.
Eliza
To: eliza_bo...@hotmail.com
Subject: Re: [R] distance from fitted line
From: joachim.audena...@pcsierteelt.be
Date: Mon, 20 Oct 2014 11:11:21 +0200
Hello Eliza,
I'm quite new to R, but I use the residuals
function to calculate the distance from my data points to the fitted line
of my nls (non linear least squares model).
residuals(name of your fitted model)
I would check for a model that fits
your datapoints and then calculate the residuals of the model to your data.
Why do you fit the generalized Extreme Value distribution
to your points in stead
of a regression model?
Met vriendelijke groeten/Kind Regards,
Joachim Audenaert
onderzoeker gewasbescherming
PCS |
proefcentrum voor sierteelt
Schaessestraat 18, 9070
Destelbergen, Belgi�
T: +32 (0)9 353 94 71 | F: +32 (0)9 353 94 95
E: joachim.audena...@pcsierteelt.be
| W: www.pcsierteelt.be
>> KEN JIJ DE
8 BASISPRINCIPES VAN IPM? MEER INFO OP WWW.PCSIERTEELT.BE
From:
eliza botto <eliza_bo...@hotmail.com>
To:
"r-help@r-project.org"
<r-help@r-project.org>
Date:
19/10/2014 22:08
Subject:
[R] distance
from fitted line
Sent by:
r-help-boun...@r-project.org
Dear useRs,
I have the following dataset.
> dput(EB)
c(77.724, 76.708, 84.836, 85.09, 118.11, 65.024, 121.412, 63.5, 102.87,
81.3, 108.7, 110.7, 71.9, 42.2, 101, 151.4, 94, 112, 48, 73.4, 76.6, 62.2,
59.4, 114.3, 214.3, 110.5, 46, 84.7, 128.1, 45.2, 109.5, 102.3, 77.5, 61,
97.3, 78, 142, 88.2, 54, 91.4, 54.1, 96, 143.3, 153.7, 101.5, 95.8, 101,
131, 140, 189.4)
I fitted generalized Extreme Value distribution on it by using following
codes
library(nsRFA)
q=EB
lmom=Lmoments(q)
pr = par.GEV (lambda1=lmom["l1"], lambda2=lmom["l2"],
tau3=lmom["lca"])
RP = c(1.01,2, 10, 20, 50, 100, 200, 500)
quant = invF.GEV (1-1/RP, pr$xi, pr$alfa, pr$k)
qs = sort(q)
pp = 1:length(qs)/(length(qs)+1)
RPpp = 1/(1-pp)
plot(RP, quant, type="l", log="x",col="black",ylim=c(0,500),xlim=c(0.1,500))
points(RPpp, qs)
What I want to do now is to calculate the distance of all the points from
the "fitted line" and ultimately calculating RMSE of the data.
Is there a way of doing it?
Thankyou very much in advance
Eliza
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
PCS-proeven
leiden tot nieuwe erkenningen in de sierteelt
| Het
PCS op LinkedIn
Disclaimer\ | Please consider the environment before pri...{{dropped:6}}
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
