[R] Probability for ANOVA

[Peter Dalgaard]

Laurent Houdusse <l.houdusse at cerep.fr> writes:

> Hi all!
> 
> I have  4 treatments on 5 animals
>            Treat1   Treat2    Treat3    Treat4
> Animal1      36       37        35       39
> Animal2      33       34        36       37
> Animal3      37       35        33       38
> Animal4      34       36        34       35
> Animal5      35       36        33       36
> 
> I use an Anova and i try to verify calcul
> So i retrieve:
>                     DF      SS       MS      F       P
> Between Groups       3    20.950   6.983   3.492
> Residual            16    32.000   2.000
> Total               19    52.950   2.787
> 
> How can i calcul the p-Value? Is there a function to do this?

Yes:

> 1-pf(3.492,3,16)
[1] 0.04032243

However, this might not be the appropriate analysis if the animals are
the same across treatments (not that it matters much in this case):

> summary(aov(y ~ treat, data=dd))
            Df Sum Sq Mean Sq F value  Pr(>F)
treat        3 20.950   6.983  3.4917 0.04033 *
Residuals   16 32.000   2.000
---
Signif. codes:  0 `***' 0.001 `**' 0.01 `*' 0.05 `.' 0.1 ` ' 1
> summary(aov(y ~ treat+animal, data=dd))
            Df  Sum Sq Mean Sq F value  Pr(>F)
treat        3 20.9500  6.9833  3.9343 0.03623 *
animal       4 10.7000  2.6750  1.5070 0.26146
Residuals   12 21.3000  1.7750
---
Signif. codes:  0 `***' 0.001 `**' 0.01 `*' 0.05 `.' 0.1 ` ' 1


-- 
   O__  ---- Peter Dalgaard             Blegdamsvej 3  
  c/ /'_ --- Dept. of Biostatistics     2200 Cph. N   
 (*) \(*) -- University of Copenhagen   Denmark      Ph: (+45) 35327918
~~~~~~~~~~ - (p.dalgaard at biostat.ku.dk)             FAX: (+45) 35327907