+ Reply to Thread
Results 1 to 4 of 4

Thread: One Sample Kolmogorov-Smirnov in Excel

  1. #1
    Registered User
    Join Date
    09-20-2011
    Location
    Monterrey
    MS-Off Ver
    Excel 2007
    Posts
    1

    One Sample Kolmogorov-Smirnov in Excel

    Hi everyone,

    Attached you will find one sample Kolmogorov-Smirnov in Excel, many people have asked how to do this in excel without using a statistical software, so enjoy it!,

    Regards!
    Attached Files Attached Files
    Last edited by Paul; 12-16-2011 at 02:36 PM.

  2. #2
    Registered User
    Join Date
    12-10-2011
    Location
    Albany, NY
    MS-Off Ver
    Excel 2011 Mac
    Posts
    1

    Re: One Sample Kolmogorov-Smirnov in Excel

    I'm a n00b too, but I don't see any attachment. I'm working on this myself, so I will post an *actual* working attachment when/if I get it working.

    Pretty easy to do KSI tests in Matlab, but I need to do it for a bunch of different datasets, so Excel fits my needs better in this case.

  3. #3
    Registered User
    Join Date
    11-03-2008
    Location
    India
    MS-Off Ver
    Excel 2007
    Posts
    1,697

    Re: One Sample Kolmogorov-Smirnov in Excel

    Hello Guys,

    I am not aware of the aforesaid test but because I found this link intersting out of curiosity I thougt of suggesting something..
    Like me there would be so many who would not hail from a Typical Mathematical or a Statistical Background..
    So can you guys actually cite an example with the above application..Just a humble request..

    Warm regards
    e4excel

  4. #4
    Registered User
    Join Date
    05-09-2012
    Location
    Monterrey, Mexico
    MS-Off Ver
    Excel 2003
    Posts
    1

    Re: One Sample Kolmogorov-Smirnov in Excel

    Hello, everyone!

    Yes, we did this One-Sample Kolmogorov-Smirnov in Excel, just to prove it could be easily witten. We checked it against SPSS.
    Obviously you can get the same information from a lot of "professional" statistical packages... but it's Excel you have on your computer, right?

    For those not familiar with the basics, just remember that if your scale data (example: weight in kg) do not have a gaussian (bell shaped) distribution, you should NOT describe them in terms of average, variance and confidence intervals. So, to find out if your data adapt to this "normal" distribution, you should run a KS test. If the probability (p) of your data's distribution being normal is to low (let's say, <0.05) you should make use of more "robust" descriptive statistics such as median, interquartile range and identification of outliers.
    Hope this helps.
    Last edited by Paul; 05-09-2012 at 01:40 AM. Reason: Removed e-mail address from post to prevent spam.

+ Reply to Thread

Thread Information

Users Browsing this Thread

There are currently 1 users browsing this thread. (0 members and 1 guests)

Tags for this Thread

Bookmarks

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts

Search Engine Friendly URLs by vBSEO 3.2.0