SPSS Statistics

SPSS Statistics

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


#Analytics
#SPSSStatistics
#Analyticstools
 View Only

  • 1.  Excel to SPSS errors

    Posted 12/05/22 12:06 PM
    Hi Rick,
    Sometimes my students delete data from an Excel cell on a spreadsheet prior to emailing me the file. Once I am in receivership of the file and transfer the data into SPSS, I see that SPSS refers to these deleted cells as missing data. This becomes obvious when, for example, I conduct frequency statistics and there is a discrepancy between valid percent and percent. SPSS also provides a row for missing data and provides a value. 

    When explaining the missing data to my students, I tell them that SPSS is attempting to read ghost cells from the Excel file. Does IBM have a specific term for this occurrence? 
    Thanks, Cliff

    #SPSSStatistics


  • 2.  RE: Excel to SPSS errors

    Posted 12/05/22 12:34 PM
    Edited by System Admin 01/20/23 04:21 PM
    Hi. If I understand you correctly, you are referring to the two kinds of missing data that users find in SPSS.

    The first - what you called the "ghost cell", I think - SPSS refers to as "system-missing" (or "sysmis") data. No meaningful value is associated with it (in either the output or the data editor; you just see a dot (".")). This most often happens when a subject provides no data for a given variable.

    The second type is called "user missing" data (see the MISSING VALUES command). Here, the subject may have provided data, but the analyst wants it treated as invalid for whatever reason. Most often, data are treated as user-missing when a response or set of responses are not appropriate, or do not apply, to them. For example, a subject responds that they are currently unemployed. Therefore, any variables measuring aspects of their current employment do not apply.






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



  • 3.  RE: Excel to SPSS errors

    Posted 12/05/22 12:52 PM
    Adding to what Rick said.  I wouldn't call these ghost cells in Excel.  They are real cells, but their values are in some sense bad.  They come into SPSS Statistics as system-missing values (".") if the contents of the cell are empty, inconsistent with the variable type in Statistics, null, or something like an invalid formula or #N/A in Excel.  Interestingly, Excel doesn't appear to have a name for these.  They just call it #N/A.





Related Content