R help - Sep 2004 - KS test

Dear all,

I have a question about the ks.test() function, in order to perform a 
Kolmogorov-Smirnov test.

I think that my question is very simple for many of you, but I cannot find 
an answer right now...

I have a sample, and I want to test if its distribution is normal. So I 
would like to perform a one sample KS test but I cannot find the "y" 
argument representing  the "character string naming a distribution 
function" according to the ?ks.test help page.
It is impossible forme to have a list of these character strings naming a 
distribution function.

I think it is "pnorm" for a normal distribution, bu I would like to be
sure...

Thanks a lot for your help,

Florence.
PS: I know that the KS test is not the best test for normality, I also 
performed the Shapiro-Wilk test.

Dear Florence,

you should specify parameters of normal distribution
(mean and sd) see this example.

 z<-rnorm(100,2,10)
ks.test(z,pnorm,2,10)

One-sample Kolmogorov-Smirnov test

data:  z 
D = 0.0508, p-value = 0.9585
alternative hypothesis: two.sided 


best
Vito
You wrote:

Dear all,

I have a question about the ks.test() function, in
order to perform a 
Kolmogorov-Smirnov test.

I think that my question is very simple for many of
you, but I cannot find 
an answer right now...

I have a sample, and I want to test if its
distribution is normal. So I 
would like to perform a one sample KS test but I
cannot find the "y" 
argument representing  the "character string naming a
distribution 
function" according to the ?ks.test help page.
It is impossible forme to have a list of these
character strings naming a 
distribution function.

I think it is "pnorm" for a normal distribution, bu I
would like to be sure...

Thanks a lot for your help,

Florence.
PS: I know that the KS test is not the best test for
normality, I also 
performed the Shapiro-Wilk test.

Dear Florence,

you should specify parameters of normal distribution
(mean and sd) see this example.


 x<-rnorm(100)
> ks.test(x,pnorm,0,1)
One-sample Kolmogorov-Smirnov test

data:  x 
D = 0.164, p-value = 0.009235
alternative hypothesis: two.sided 


====Diventare costruttori di soluzioni

"The business of the statistician is to catalyze 
the scientific learning process."  
George E. P. Box


Visitate il portale http://www.modugno.it/
e in particolare la sezione su Palese
http://www.modugno.it/archivio/cat_palese.shtml


		
___________________________________

http://it.seriea.fantasysports.yahoo.com/

Hi,

> I have a sample, and I want to test if its distribution is normal. So I
> would like to perform a one sample KS test but I cannot find the
"y"
> argument representing  the "character string naming a distribution
> function" according to the ?ks.test help page.
> It is impossible forme to have a list of these character strings naming a
> distribution function.
> 
> I think it is "pnorm" for a normal distribution, bu I would like
to be sure...
> 
>From examples in ks.test manual:
# Does x come from a shifted gamma distribution with shape 3 and scale 2?
     ks.test(x+2, "pgamma", 3, 2) # two-sided
     ks.test(x+2, "pgamma", 3, 2, alternative = "gr")

So you can be sure, that it will be "pnorm" for normal distribution.

Vaidotas