Skip to content

modified kolmogorov-smirnov

3 messages · Martín Marqués, Brian Ripley

Original
Martín Marqués
# 
I'm trying to use modified Kolmogorov-Smirnov test with a Normal which I
don't know it's parameters. Somebody told me about the lilifor function in
R, but just can't find it.
Does anybody know how I can test with the modified Kolmogorov-Smirnov
test?


Porqu? usar una base de datos relacional cualquiera,
si pod?s usar PostgreSQL?
-----------------------------------------------------------------
Mart?n Marqu?s                  |        mmarques at unl.edu.ar
Programador, Administrador, DBA |       Centro de Telematica
                       Universidad Nacional
                            del Litoral
-----------------------------------------------------------------


-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
Martín Marqués
# 
Don't worry, I think I got the answer. If you don't give ks.test() the
parameters for the normal, it does the modified K-S test (I'm right
ain't I?).

Saludos... :-)
On Mon, 1 Jul 2002, Mart?n Marqu?s wrote:

            

      
      
      
    

        
Porqu? usar una base de datos relacional cualquiera,
si pod?s usar PostgreSQL?
-----------------------------------------------------------------
Mart?n Marqu?s                  |        mmarques at unl.edu.ar
Programador, Administrador, DBA |       Centro de Telematica
                       Universidad Nacional
                            del Litoral
-----------------------------------------------------------------

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._

  
  


  


      

    

    

      
      

        


  

        

      Brian Ripley
    

    

      
      #
    

  


  

      
On Mon, 1 Jul 2002, [iso-8859-1] Martín Marqués wrote:

        

            

      
      
      
    

        
Did you read either the help page or the code?  Or even do an experiment:

            

      
      
      
    

        
One-sample Kolmogorov-Smirnov test

data:  x
D = 1, p-value = < 2.2e-16
alternative hypothesis: two.sided

So, `it ain't', and we do now start to worry.

Why do you want to do this test anyway?

1) There are better tests of normality and
2) Almost always the amount of non-normality that might affect the
substantive conclusions is unrelated to the signifcance of a test
statistic.