Hey,
Doesn't this give you a ridiculous Type 1 error? Maybe randomly select one
result and trust it.
Try bestglm or stepwise regression maybe.
Hope that's helpful,
Ken Hutchison
On Oct 14, 2554 BE, at 12:39 AM, "C.H." wrote:
> This is one solution
>
> ?sapply
>
> sa
This is one solution
?sapply
sapply(data.frame(iris$Sepal.Length, iris$Sepal.Width,
iris$Petal.Length, iris$Petal.Width), function(x)
(summary(aov(x~iris$Species
On Tue, Oct 11, 2011 at 5:10 PM, Joshua Wong wrote:
> Hi Guys,
>
> I have about 20 continous predictors and I want to do one-wa
Hi Guys,
I have about 20 continous predictors and I want to do one-way anova to check
the significance of each variable against the dependent variable.
Apart from doing running the anova 20 times, is there a faster way?
Thanks,
Joshua
[[alternative HTML version deleted]]
___
3 matches
Mail list logo