Dear Peter,
Thank you very much for that excellent answer to a rather stupid question :)
I did not notice that the RSS actually increased for the model with more
parameters and so in this case the F-statistic is negative and therefore a
p-value from the F-distribution is meaningless. But I guess y
On Jul 9, 2012, at 15:40 , Suresh Krishna wrote:
>
> Hello,
>
> Why does anova.lm sometimes return a p-value and at other times not ? Is it
> because it recognizes nested models from non-nested ones ?
>
>> x<-seq(1,100,1)
>> y<-3*x+rnorm(100)
>> anova(lm(y~x),lm(y~x+I(x^2)),test="F")
> Analy
Hello,
Why does anova.lm sometimes return a p-value and at other times not ? Is
it because it recognizes nested models from non-nested ones ?
x<-seq(1,100,1)
y<-3*x+rnorm(100)
anova(lm(y~x),lm(y~x+I(x^2)),test="F")
Analysis of Variance Table
Model 1: y ~ x
Model 2: y ~ x + I(x^2)
Res.D
3 matches
Mail list logo
