SPSS Statistics

SPSS Statistics

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

 View Only
  • 1.  post-hoc comparisons after Kruskal Wallis test

    Posted Thu February 17, 2022 02:02 PM
    Hello everyone!

    I applied the Kruskal Wallis test between an independent variable with 3 categories and 3 dependent variables. The test was significant.

    I was wondering in which way I can see which combination of groups are significant since
    I cannot apply Mann-Whitney tests and bonferroni correction.

    Any ideas?

    Thanks a lot!

    Sandy.

    #SPSSStatistics


  • 2.  RE: post-hoc comparisons after Kruskal Wallis test

    Posted Thu February 17, 2022 02:10 PM
    Hi, Sandy.

    Did you use the NPTESTS command? Something like this:

    ```
    NPTESTS
    /INDEPENDENT TEST (dv1 dv2 dv3) GROUP (catvar3)
    KRUSKAL_WALLIS(COMPARE=PAIRWISE)
    /MISSING SCOPE=ANALYSIS USERMISSING=EXCLUDE
    /CRITERIA ALPHA=0.05 CILEVEL=95.
    ```

    ------------------------------
    Rick Marcantonio
    Quality Assurance
    IBM
    ------------------------------



  • 3.  RE: post-hoc comparisons after Kruskal Wallis test

    Posted Fri February 18, 2022 01:21 PM
    Hi,
    Thank you so much for the reply.
    I tried it but I am afraid I have trouble with the syntax.
    Is there another test I could run from the menu-analysis-etc?

    Best,
    Sandy

    Στις Πέμ 17 Φεβ 2022 στις 9:12 μ.μ., ο/η Rick Marcantonio via IBM Community <Mail@connectedcommunity.org> έγραψε:
    Hi, Sandy. Did you use the NPTESTS command? Something like this: ``` NPTESTS /INDEPENDENT TEST (dv1 dv2 dv3) GROUP (catvar3) KRUSKAL_WALLIS... -posted to the "SPSS Statistics" group
    IBM Community

    SPSS Statistics

    Post New Message
    Re: post-hoc comparisons after Kruskal Wallis test
    Reply to Group Reply to Sender
    Rick Marcantonio
    Feb 17, 2022 2:10 PM
    Rick Marcantonio
    Hi, Sandy.

    Did you use the NPTESTS command? Something like this:

    ```
    NPTESTS
    /INDEPENDENT TEST (dv1 dv2 dv3) GROUP (catvar3)
    KRUSKAL_WALLIS(COMPARE=PAIRWISE)
    /MISSING SCOPE=ANALYSIS USERMISSING=EXCLUDE
    /CRITERIA ALPHA=0.05 CILEVEL=95.
    ```

    ------------------------------
    Rick Marcantonio
    Quality Assurance
    IBM
    ------------------------------
      Reply to Group Online   View Thread   Recommend   Forward  




     
    You are receiving this notification because you followed the 'post-hoc comparisons after Kruskal Wallis test' message thread. If you do not wish to follow this, please click here.

    Update your email preferences to choose the types of email you receive

    Unsubscribe from all participation emails




    Original Message:
    Sent: 2/17/2022 2:10:00 PM
    From: Rick Marcantonio
    Subject: RE: post-hoc comparisons after Kruskal Wallis test

    Hi, Sandy.

    Did you use the NPTESTS command? Something like this:

    ```
    NPTESTS
    /INDEPENDENT TEST (dv1 dv2 dv3) GROUP (catvar3)
    KRUSKAL_WALLIS(COMPARE=PAIRWISE)
    /MISSING SCOPE=ANALYSIS USERMISSING=EXCLUDE
    /CRITERIA ALPHA=0.05 CILEVEL=95.
    ```

    ------------------------------
    Rick Marcantonio
    Quality Assurance
    IBM
    ------------------------------


  • 4.  RE: post-hoc comparisons after Kruskal Wallis test

    Posted Fri February 18, 2022 01:28 PM
    1. Analyze > Nonparametric Tests > Independent Samples ...
    2. Click the "Fields" tab at the top of that dialog
    3. Move the dependent variables you want into the "Test Fields" box
    4. Move the grouping variable into the Groups box
    5. Click the "Settings" tab at the top of that dialog
    6. Select "Customize tests"
    7. Select Kruskal-Wallis 1-way ANOVA (k samples)
    8. Select Run at the bottom of that dialog.

    That should do it, Sandy.

    ------------------------------
    Rick Marcantonio
    Quality Assurance
    IBM
    ------------------------------



  • 5.  RE: post-hoc comparisons after Kruskal Wallis test

    Posted Sat February 19, 2022 10:32 AM
    Hi Rick,

    That worked perfectly! Thank you!
    Would it be useful if I run a Jonckheere-terpstra test as well?


    Best,
    Sandy



    Στις Παρ 18 Φεβ 2022 στις 8:29 μ.μ., ο/η Rick Marcantonio via IBM Community <Mail@connectedcommunity.org> έγραψε:
    1. Analyze > Nonparametric Tests > Independent Samples ... 2. Click the "Fields" tab at the top of that dialog 3. Move the dependent variables you...
    IBM Community

    SPSS Statistics

    Post New Message
    Re: post-hoc comparisons after Kruskal Wallis test
    Reply to Group Reply to Sender
    Rick Marcantonio
    Feb 18, 2022 1:28 PM
    Rick Marcantonio
    1. Analyze > Nonparametric Tests > Independent Samples ...
    2. Click the "Fields" tab at the top of that dialog
    3. Move the dependent variables you want into the "Test Fields" box
    4. Move the grouping variable into the Groups box
    5. Click the "Settings" tab at the top of that dialog
    6. Select "Customize tests"
    7. Select Kruskal-Wallis 1-way ANOVA (k samples)
    8. Select Run at the bottom of that dialog.

    That should do it, Sandy.

    ------------------------------
    Rick Marcantonio
    Quality Assurance
    IBM
    ------------------------------
      Reply to Group Online   View Thread   Recommend   Forward  




     
    You are receiving this notification because you followed the 'post-hoc comparisons after Kruskal Wallis test' message thread. If you do not wish to follow this, please click here.

    Update your email preferences to choose the types of email you receive

    Unsubscribe from all participation emails




    Original Message:
    Sent: 2/18/2022 1:28:00 PM
    From: Rick Marcantonio
    Subject: RE: post-hoc comparisons after Kruskal Wallis test

    1. Analyze > Nonparametric Tests > Independent Samples ...
    2. Click the "Fields" tab at the top of that dialog
    3. Move the dependent variables you want into the "Test Fields" box
    4. Move the grouping variable into the Groups box
    5. Click the "Settings" tab at the top of that dialog
    6. Select "Customize tests"
    7. Select Kruskal-Wallis 1-way ANOVA (k samples)
    8. Select Run at the bottom of that dialog.

    That should do it, Sandy.

    ------------------------------
    Rick Marcantonio
    Quality Assurance
    IBM
    ------------------------------

    Original Message:
    Sent: Fri February 18, 2022 01:20 PM
    From: Sandy Lioupi
    Subject: post-hoc comparisons after Kruskal Wallis test

    Hi,
    Thank you so much for the reply.
    I tried it but I am afraid I have trouble with the syntax.
    Is there another test I could run from the menu-analysis-etc?

    Best,
    Sandy

    Στις Πέμ 17 Φεβ 2022 στις 9:12 μ.μ., ο/η Rick Marcantonio via IBM Community <Mail@connectedcommunity.org> έγραψε:
    Hi, Sandy. Did you use the NPTESTS command? Something like this: ``` NPTESTS /INDEPENDENT TEST (dv1 dv2 dv3) GROUP (catvar3) KRUSKAL_WALLIS... -posted to the "SPSS Statistics" group
    IBM Community

    SPSS Statistics

    Post New Message
    Re: post-hoc comparisons after Kruskal Wallis test
    Reply to Group Reply to Sender
    Rick Marcantonio
    Feb 17, 2022 2:10 PM
    Rick Marcantonio
    Hi, Sandy. Did you use the NPTESTS command? Something like this: ``` NPTESTS /INDEPENDENT TEST (dv1 dv2 dv3) GROUP (catvar3) KRUSKAL_WALLIS(COMPARE=PAIRWISE) /MISSING SCOPE=ANALYSIS USERMISSING=EXCLUDE /CRITERIA ALPHA=0.05 CILEVEL=95. ``` ------------------------------ Rick Marcantonio Quality Assurance IBM ------------------------------
      Reply to Group Online   View Thread   Recommend   Forward  
    Original Message: Sent: Thu February 17, 2022 02:01 PM
     
    You are receiving this notification because you followed the 'post-hoc comparisons after Kruskal Wallis test' message thread. If you do not wish to follow this, please click here.

    Update your email preferences to choose the types of email you receive

    Unsubscribe from all participation emails




    Original Message:
    Sent: 2/17/2022 2:10:00 PM
    From: Rick Marcantonio
    Subject: RE: post-hoc comparisons after Kruskal Wallis test

    Hi, Sandy.

    Did you use the NPTESTS command? Something like this:

    ```
    NPTESTS
    /INDEPENDENT TEST (dv1 dv2 dv3) GROUP (catvar3)
    KRUSKAL_WALLIS(COMPARE=PAIRWISE)
    /MISSING SCOPE=ANALYSIS USERMISSING=EXCLUDE
    /CRITERIA ALPHA=0.05 CILEVEL=95.
    ```

    ------------------------------
    Rick Marcantonio
    Quality Assurance
    IBM
    ------------------------------

    #SPSSStatistics


  • 6.  RE: post-hoc comparisons after Kruskal Wallis test

    Posted Mon February 21, 2022 02:17 PM
    That depends on your hypothesis or hypotheses. Check here to see the assumption of the JT test.

    ------------------------------
    Rick Marcantonio
    Quality Assurance
    IBM
    ------------------------------