+ Reply to Thread
Results 1 to 5 of 5

Thread: Predicting outcome with multiple groups

  1. #1
    Points: 1,723, Level: 24
    Level completed: 23%, Points required for next Level: 77

    Posts
    4
    Thanks
    1
    Thanked 0 Times in 0 Posts

    Predicting outcome with multiple groups




    Hi everyone,

    I'm currently working with 3 different groups (3 disease populations) and I would like to predict which of the three groups they fall into based on a measurement we did. I was thinking that it should be something like multinominal logistic regression but how can I then get a vector out to predict the response in the future?

    Best,

    Eric

  2. #2
    Omega Contributor
    Points: 38,303, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    6,993
    Thanks
    397
    Thanked 1,185 Times in 1,146 Posts

    Re: Predicting outcome with multiple groups

    Yeah, multinominal logistic sounds fine. What do you need to predict in the future exactly?
    Stop cowardice, ban guns!

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

    Eric2014 (03-28-2017)

  4. #3
    Points: 1,723, Level: 24
    Level completed: 23%, Points required for next Level: 77

    Posts
    4
    Thanks
    1
    Thanked 0 Times in 0 Posts

    Re: Predicting outcome with multiple groups

    Thanks a lot for your comment hlsmith!

    I would like to use the dataset I have now to predict new cases in the future. For example, predicting which one of the three groups a new subject would be classified as if I recruited one more subject and wanted to know if that one had disease 1, 2 or 3.

    Thanks in advance,

    Eric

  5. #4
    Omega Contributor
    Points: 38,303, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    6,993
    Thanks
    397
    Thanked 1,185 Times in 1,146 Posts

    Re: Predicting outcome with multiple groups

    So what is the "measurement" you did. So do you have a continuous variable you are looking to use to trichotomize patients with? Or do you have multiple predictors?
    Stop cowardice, ban guns!

  6. #5
    Points: 1,723, Level: 24
    Level completed: 23%, Points required for next Level: 77

    Posts
    4
    Thanks
    1
    Thanked 0 Times in 0 Posts

    Re: Predicting outcome with multiple groups


    Yes, I'm planning to use electrophysiological measures (continuous variables). It would be interesting to use multiple predictors but first of all it's about one predictor.

    Thanks a lot,

    Eric

+ Reply to Thread

           




Tags for this 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