+ Reply to Thread
Results 1 to 5 of 5

Thread: "Sensitivty" analysis

  1. #1
    Fortran must die
    Points: 58,790, Level: 100
    Level completed: 0%, Points required for next Level: 0
    noetsi's Avatar
    Posts
    6,532
    Thanks
    692
    Thanked 915 Times in 874 Posts

    "Sensitivty" analysis




    I have not encountered this before. It occurs in the context of "mixed effects OLS regression" (not sure exactly what type of regression that is...

    Sensitivity analysis and the boosted regression technique (see pg. 12) helped to validate our regression results. Sensitivity analysis involves making small changes to the regression specification. The way in which estimates react to small changes gives the researcher clues about the validity of the model, and can also draw attention to issues that still need to be resolved. If the estimated effect of the variable in question changes drastically due to changes in other variables, or by changing the functional form, then the estimates are not trustworthy.
    "Very few theories have been abandoned because they were found to be invalid on the basis of empirical evidence...." Spanos, 1995

  2. #2
    Omega Contributor
    Points: 38,289, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    6,992
    Thanks
    397
    Thanked 1,185 Times in 1,146 Posts

    Re: "Sensitivty" analysis

    Sensitivity analysis is anything you want to do to test the robustness of results. It widely varies and you can perform it on any type of statistic from wilcoxon to survival to meta analysis.
    Stop cowardice, ban guns!

  3. The Following User Says Thank You to hlsmith For This Useful Post:

    noetsi (03-18-2016)

  4. #3
    Fortran must die
    Points: 58,790, Level: 100
    Level completed: 0%, Points required for next Level: 0
    noetsi's Avatar
    Posts
    6,532
    Thanks
    692
    Thanked 915 Times in 874 Posts

    Re: "Sensitivty" analysis

    They changed the values of various predictors and saw how this influenced the results. They stressed stability I assume this means when they changed the predictor values it did not lead to major changes in the slope. It is not clear to me how much you would vary the predictors this way [1 percent, 10 percent...]

    When you changed the predictor values a specific amount do you add the same amount to the Y variables as well?
    "Very few theories have been abandoned because they were found to be invalid on the basis of empirical evidence...." Spanos, 1995

  5. #4
    Omega Contributor
    Points: 38,289, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    6,992
    Thanks
    397
    Thanked 1,185 Times in 1,146 Posts

    Re: "Sensitivty" analysis

    If you think a related variable is misclassified or poorly collected, poosibly also selction bias, you can see how extreme of values it would have taken to make estimates null.

    My area has really pushed, when running anályses, after done, to perform sensitivity analysis.
    Stop cowardice, ban guns!

  6. #5
    Fortran must die
    Points: 58,790, Level: 100
    Level completed: 0%, Points required for next Level: 0
    noetsi's Avatar
    Posts
    6,532
    Thanks
    692
    Thanked 915 Times in 874 Posts

    Re: "Sensitivty" analysis


    I use them when predicting future spending where there is great uncertainty. If we are off by this much the results will be...

    It makes sense in your field to do sensitivity analysis. If we are wrong by this much lawsuits will cost X amount... (j/k)
    "Very few theories have been abandoned because they were found to be invalid on the basis of empirical evidence...." Spanos, 1995

+ Reply to Thread

           




Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts






Advertise on Talk Stats