Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: st: ksmirnov


From   "Guessab Houda" <[email protected]>
To   <[email protected]>
Subject   RE: st: ksmirnov
Date   Tue, 21 Aug 2012 10:30:47 +0200

Dear Nick,

I can understand your point...you are absolutely right but i need just to know how to do it and then to prove that it's wrong (It was applied by a colleague with Matlab).to compare with a normal distribution we write: Ksmirnov x = norm(x-r(mean)/r(sd))

With student distribution 8 degrees, instead of norm (),we can put ttail(8, x) ? 

However, I appreciate your help and sorry to bother you...

Houda GUESSAB

 


-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of Nick Cox
Sent: lundi 20 août 2012 18:40
To: [email protected]
Subject: Re: st: ksmirnov

I am disinclined to support what I guess is likely to be wrong in
principle, but -help density functions- guides you on functions for t
distributions.

Nick

On Mon, Aug 20, 2012 at 5:16 PM, Guessab Houda
<[email protected]> wrote:
> Thank you nick,
>
> Apologies for posting anonymous question... this is such a good idea to make quantile quantile plot. The thing is that I have to use kormogolov smirnov but I really don't know how to apply it to a distribution with t with 8 d.f.Could you please help me?

>
>
> Houda GUESSAB
>
>
>
>
>
> -----Original Message-----
> From: [email protected] [mailto:[email protected]] On Behalf Of Nick Cox
> Sent: lundi 20 août 2012 17:40
> To: [email protected]
> Subject: Re: st: ksmirnov
>
> Naturally I agree with Maarten on the point of list practice. He is
> referring to an explicit request that posters use their full names.
> 2.1.3 within http://www.stata.com/support/faqs/resources/statalist-faq/#tojoin
>  means exactly what it says.
>
> On the substantive question,
>
> (1) if "series" means what I think it does, a time series of some
> kind, then note that Kolmogorov-Smirnov tests tacitly assume mutual
> independence
>
> (2) the most direct way of comparing a distribution with t with 8 d.f.
> is a quantile-quantile plot.
>
> Example code to show how easy this is:
>
> sysuse auto, clear
> egen rank = rank(mpg), unique
> su mpg, meanonly
> local N = r(N)
> gen tquantile = -invttail(8, (rank - 0.5) / `N')
> scatter mpg tquantile
>
>
> On Mon, Aug 20, 2012 at 4:17 PM, Maarten Buis <[email protected]> wrote:
>> On Mon, Aug 20, 2012 at 5:05 PM, houda wrote:
>>> I m trying to find a simple way to test if a series is t-distributed with 8
>>> degrees
>>> of freedom using a Kolmogorov-Smirnov test, could you please help me?
>>
>> Policy on the statalist is not to post anonymous questions. This is
>> clearly explained in the Statalist FAQ.

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/

 
Ai sensi del D.Lgs. 196/2003 si precisa che le informazioni contenute in questo messaggio sono riservate ed a uso esclusivo del destinatario. Qualora il messaggio in parola Le fosse pervenuto per errore, La invitiamo ad eliminarlo senza copiarlo e a non inoltrarlo a terzi, dandocene gentilmente comunicazione. Grazie.

Pursuant to Legislative Decree No. 196/2003, you are hereby informed that this message contains confidential information intended only for the use of the addressee. If you are not the addressee, and have received this message by mistake, please delete it and immediately notify us. You may not copy or disseminate this message to anyone. Thank you.

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index