SPSS Statistics

SPSS Statistics

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

 View Only

  • 1.  Data input

    Posted Mon April 04, 2022 09:36 AM

    Hello, 

    have variables that used differing likert scales. 

    study calls for one way ANOVA

    tried doing a check for outliers with box plot, but has outliers. 

    data is sound since responses were imported and were likert scale number values. 

    SPSS guide says can't use one way ANOVA if outliers exist. 

    is anyone available to screen share in Teams to point me in the right direction? If so please reply and I can send an invite? Thank you 



    ------------------------------
    Patrice Chandler
    ------------------------------


    #SPSSStatistics


  • 2.  RE: Data input

    Posted Mon April 04, 2022 10:01 AM
    This is a direct copy from a webpage but sums up exactly what your options are.

    Dealing with outliers

    Once a potential outlier has been identified, first check the data to make sure the outlier is not a data entry or data coding error. If not you can conduct a sensitivity analysis as follows to see how much the outlying observations affect your results.

    • Run ANOVA on the entire data.
    • Remove outlier(s) and rerun the ANOVA.
    • If the results are the same then you can report the analysis on the full data and report that the outliers did not influence the results.
    • If the results are different, try running a non-parametric test (e.g. Kruskal-Wallis) or simply report your analysis with and without the outlier.

    Two other approaches for dealing with outliers are to use trimmed means or Winsorized samples (as described in Outliers and Robustness) or to use a transformation. In particular, a reciprocal transformation f(x) = 1/x can be useful.



    ------------------------------
    Kate Clark
    ------------------------------

    Original Message


  • 3.  RE: Data input

    Posted Mon April 04, 2022 11:18 AM
    This is a common  misunderstanding.  The outlier issue pertains to errorsfrom the model, not the actual dependent variable.  After all, a factor value that has a very large effect might make all the cases for that factor appear to be outliers if you just looked at the dependent variable values.

    So, to check for outliers, save the residuals from the ANOVA - you need to use General Linear Models > Univariate,  I would recommend the deleted residuals.  Then you can look at those for problems.



    --



    Original Message