SPSS Statistics

SPSS Statistics

Your hub for statistical analysis, data management, and data documentation. Connect, learn, and share with your peers! 

 View Only

  • 1.  Kolmogorov-Smirnov vs Shapiro-Wilk

    Posted Mon August 10, 2020 09:08 AM

    What is the consequence of having a Significant statistic in Kolmogorov-Smirnov Test but the Shapiro-Wilk test result is non-significant?






    #SPSSStatistics
    #Support
    #SupportMigration


  • 2.  RE: Kolmogorov-Smirnov vs Shapiro-Wilk

    Posted Mon August 10, 2020 10:54 AM

    Dear Support Member​ .

     

    If the question is related to statistics, implementation, coding, general troubleshooting, please log your query on the following link:

     

    And then please Ask our SPSS Statistics community and get answers from other users and experts worldwide.

     

    This forum is mainly for question related to technical support question for licensing, errors, installation, fix packs, trial set-up.

     

    Best regards.

    Support Member​ 

     






    #SPSSStatistics
    #Support
    #SupportMigration


  • 3.  RE: Kolmogorov-Smirnov vs Shapiro-Wilk

    Posted Mon August 10, 2020 03:36 PM

    Shapiro-Wilks is generally considered more powerful than K-S as a test of normality, but it doesn't handle ties as well. Another possibility is Anderson-Darling, which is available in the SPSS Simulation procedure.

    I wouldn't generally be concerned about what might be a mild departure from normality for most procedures, however.






    #SPSSStatistics
    #Support
    #SupportMigration