R help - Jul 2007 - change the "coeffcients approach" on an anova

hi everybody

I have to do a lot of Anova with R and I would like to have another type of
coefficients coding.. I explain.

by default if I have 2 temperatures for an experience. 100°C or 130°C and I
want to see the temperature effect on the presure
I want to estimate the coefficient of each temperature.

I will obtain ,with the anova, juste one coefficients for example +3,56 (for
100°C), and the other (for 130°C) is always  zero.

but I prefer to obtain + 1,78 or the first effect and -1,78 for the second
(the intercept is also different too)

my script is (it s just an example)

rinfo2 <- (lm(pression~ temp, data=rebe))
anova(rinfo2)
summary(rinfo2)

what can I change to obtain what I need?

best regards



-- 
_________________________________
Vincent GUYADER
École nationale supérieure d'agronomie de Rennes (ENSAR)
EN156 - Spécialité statistiques appliquées
06.22.85.34.27

	[[alternative HTML version deleted]]

On 7/7/07, vincent guyader <guyader at agrocampus-rennes.fr>
wrote:
> hi everybody
>
> I have to do a lot of Anova with R and I would like to have another type of
> coefficients coding.. I explain.
>
> by default if I have 2 temperatures for an experience. 100?C or 130?C and I
> want to see the temperature effect on the presure
> I want to estimate the coefficient of each temperature.
>
> I will obtain ,with the anova, juste one coefficients for example +3,56
(for
> 100?C), and the other (for 130?C) is always  zero.
>
> but I prefer to obtain + 1,78 or the first effect and -1,78 for the second
> (the intercept is also different too)
>
> my script is (it s just an example)
>
> rinfo2 <- (lm(pression~ temp, data=rebe))
Try:

lm(pression ~ temp + 0, rebe)


> anova(rinfo2)
> summary(rinfo2)
>
> what can I change to obtain what I need?
>
> best regards
>
>
>
> --
> _________________________________
> Vincent GUYADER
> ?cole nationale sup?rieure d'agronomie de Rennes (ENSAR)
> EN156 - Sp?cialit? statistiques appliqu?es
> 06.22.85.34.27
>
>        [[alternative HTML version deleted]]
>
>
> ______________________________________________
> R-help at stat.math.ethz.ch 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.
>
>

Un texte encapsul? et encod? dans un jeu de caract?res inconnu a ?t? nettoy?...
Nom : non disponible
Url :
https://stat.ethz.ch/pipermail/r-help/attachments/20070708/16c270e0/attachment.pl

On 08-Jul-07 00:36:46, vincent guyader wrote:
> hi everybody
> 
> I have to do a lot of Anova with R and I would like to have another
> type of
> coefficients coding.. I explain.
> 
> by default if I have 2 temperatures for an experience. 100?C or 130?C
> and I
> want to see the temperature effect on the presure
> I want to estimate the coefficient of each temperature.
> 
> I will obtain ,with the anova, juste one coefficients for example +3,56
> (for
> 100?C), and the other (for 130?C) is always  zero.
> 
> but I prefer to obtain + 1,78 or the first effect and -1,78 for the
> second
> (the intercept is also different too)
> 
> my script is (it s just an example)
> 
> rinfo2 <- (lm(pression~ temp, data=rebe))
> anova(rinfo2)
> summary(rinfo2)
> 
> what can I change to obtain what I need?
Try

  rinfo2 <- (lm(pression~temp-1, data=rebe))

Ted.

--------------------------------------------------------------------
E-Mail: (Ted Harding) <ted.harding at nessie.mcc.ac.uk>
Fax-to-email: +44 (0)870 094 0861
Date: 08-Jul-07                                       Time: 02:18:24
------------------------------ XFMail ------------------------------