SPSS Statistics

SPSS Statistics

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

 View Only
Back to discussions
Expand all | Collapse all

SPSS 26: How to choose the optimization method when using the regression tool for prediction?

  • 1.  SPSS 26: How to choose the optimization method when using the regression tool for prediction?

    Posted Thu December 22, 2022 08:53 AM

    SPSS 26: How to choose the optimization method when using the regression tool for prediction?

     

     

    I couldn't figure out how to choose the optimization method when using the regression tool for prediction.

     

    Are all techniques for regression optimization available?

     

    • The Ordinary Least Square (OLS)
    • Least Absolute Shrinkage and Selection Operator (LASSO)
    • Least Absolute Deviation (LAD)







    ------------------------------
    jamal numan
    ------------------------------

    #SPSSStatistics


  • 2.  RE: SPSS 26: How to choose the optimization method when using the regression tool for prediction?

    Posted Thu December 22, 2022 10:09 AM
    The famous Gauss-Markov theorem says that ordinary least squares is the Best Linear Unbiased Estimator (BLUE) under certain conditions.  But if you give up the unbiased requirement, you can get estimators with better squared error.  The bias-variance tradeoff is exploited in other estimators.  Google bias-variance tradeoff for many articles on this topic.

    --



    Original Message


  • 3.  RE: SPSS 26: How to choose the optimization method when using the regression tool for prediction?

    Posted Mon December 26, 2022 02:03 AM

    Do you mean that the regression in SPSS is built on the OLS with no options to choose other methods?



    ------------------------------
    jamal numan
    ------------------------------

    Original Message