iSixSigma

More regression

Six Sigma – iSixSigma Forums Old Forums General More regression

Viewing 2 posts - 1 through 2 (of 2 total)
  • Author
    Posts
  • #42794

    Lorax
    Participant

    Another odd one.
    I’ve regressed the ingredients of rubber manufacturing to try to predict seven different measurements that can be taken from finished material.
    This has generated seven predictive equations (one for each test) and seven R-squared numbers (which describe the amount of variation in the test which is explained by the predictive equation).
    But.
    When I make verification samples to see how each of the predictive equations does at predicting reality, the equation which has the worst (60%) R-squared value repeatedly has one of the highest accuracies.
    Any thoughts?
    Lorax
     

    0
    #135268

    Lorax
    Participant

    Ahha.
    The one with the contradictory R-squared and delta-from-reality has got a measuring system which, while adequate for discriminating between good and bad product, has a limited resolution.
    Problem solved?
     

    0
Viewing 2 posts - 1 through 2 (of 2 total)

The forum ‘General’ is closed to new topics and replies.