SPSS Statistics

SPSS Statistics

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

 View Only
  • 1.  Coding missing values

    Posted Sun January 07, 2024 08:23 PM

    Hello,

    when importing data into SPSS, missing values are automatically coded with -9. All the other values are between 1 and 4. 

    1. When analyzing, does SPSS include the missing values (with the value of -9)?
    2. Do I have to delete or recode them or change settings in order to SPSS recognising them as missing values? Are they automatically excluded from analysis?

    How do you handle this?

    Thank you!



    ------------------------------
    Janika Mattke
    ------------------------------



  • 2.  RE: Coding missing values

    Posted Sun January 07, 2024 09:18 PM
    No.  Missing values would not be automatically coded as -9.  That would have to be declared as a missing value code unless your data source has already done that.  You can declare missing values in the Data Editor Variable View or wih the MISSING VALUES command.

    Declared user missing values are generally omitted in statistical procedures, but this can be on a casewise or per variable basis.  Procedures vary in what method they use.

    --





  • 3.  RE: Coding missing values

    Posted Wed January 10, 2024 08:59 AM

    Hi, 

    Would you know if its possible to impute on SPSS based on specific demographics? 

    I have a large data set with a 26 question questionaire that is missing some responses. Is there a way to impute for the missing answers based on similar responses from those of the same gender/age/ethnicity?

    If so, could you please explain how/point me in the direction of a manual

    Thanks 



    ------------------------------
    Sruthi Venkatram
    ------------------------------



  • 4.  RE: Coding missing values

    Posted Wed January 10, 2024 09:40 AM
    Both single and multiple imputation are possible.  See Analyze > Missing Value Analysis or Multiple Imputation.  There are case studies for these available via Help > Topics.
    --