kSamples ad.test question

classic Classic list List threaded Threaded
2 messages Options
Reply | Threaded
Open this post in threaded view
|

kSamples ad.test question

R help mailing list-2
Dear All,

once we run the following code, the results of the test will give us the expected obvious, samples are from the common distribution...


library(kSamples)

u1 <- sample(rnorm(500,10,1),20,replace = TRUE)
u2 <- sample(rnorm(500,10,1),20,replace = TRUE)
u3 <- sample(rnorm(500,10,1),20,replace = TRUE)
u4 <- sample(rnorm(500,10,1),20,replace = TRUE)
u5 <- sample(rnorm(500,10,1),20,replace = TRUE)

ad.test(u1, u2, u3,u4,u5, method = "exact", dist = FALSE, Nsim = 1000)

next, if I change "u5" to:

u5 <- sample(rnorm(500,20,1),20,replace = TRUE)

the results of the test again gives us what we expect, ie samples are not from the common distribution.... my question is: would you know of a way to be able to automatically select out or identify  "u5", the distribution that is "responsible"  for the results generated showing that the samples are not from the common distribution? 

much appreciate your help,


Andras 

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
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.
Reply | Threaded
Open this post in threaded view
|

Re: kSamples ad.test question

Bert Gunter-2
You may get a response here, but as this is primarily a statistical
question, not a question about R programming, so it is off topic here. I
would suggest that you post this on stats.stackexchange.com or other
statistics site instead. There is a large literature on this sort of thing .

Cheers,
Bert



Bert Gunter

"The trouble with having an open mind is that people keep coming along and
sticking things into it."
-- Opus (aka Berkeley Breathed in his "Bloom County" comic strip )

On Thu, Aug 2, 2018 at 12:00 PM, Andras Farkas via R-help <
[hidden email]> wrote:

> Dear All,
>
> once we run the following code, the results of the test will give us the
> expected obvious, samples are from the common distribution...
>
>
> library(kSamples)
>
> u1 <- sample(rnorm(500,10,1),20,replace = TRUE)
> u2 <- sample(rnorm(500,10,1),20,replace = TRUE)
> u3 <- sample(rnorm(500,10,1),20,replace = TRUE)
> u4 <- sample(rnorm(500,10,1),20,replace = TRUE)
> u5 <- sample(rnorm(500,10,1),20,replace = TRUE)
>
> ad.test(u1, u2, u3,u4,u5, method = "exact", dist = FALSE, Nsim = 1000)
>
> next, if I change "u5" to:
>
> u5 <- sample(rnorm(500,20,1),20,replace = TRUE)
>
> the results of the test again gives us what we expect, ie samples are not
> from the common distribution.... my question is: would you know of a way to
> be able to automatically select out or identify  "u5", the distribution
> that is "responsible"  for the results generated showing that the samples
> are not from the common distribution?
>
> much appreciate your help,
>
>
> Andras
>
> ______________________________________________
> [hidden email] mailing list -- To UNSUBSCRIBE and more, see
> 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.
>

        [[alternative HTML version deleted]]

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
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.