+ Reply to Thread
Results 1 to 4 of 4

Thread: GLM diagnostic plots in r

  1. #1
    Points: 316, Level: 6
    Level completed: 32%, Points required for next Level: 34

    Posts
    2
    Thanks
    2
    Thanked 0 Times in 0 Posts

    Exclamation GLM diagnostic plots in r




    I am trying to fit a Gamma glm in R. getting very weird diagnostics even though all variables are significant. Please advise as to how i can improve this
    Attached Thumbnails Attached Thumbnails Click image for larger version

Name:	weird residual.jpg‎
Views:	51
Size:	16.7 KB
ID:	5345   Click image for larger version

Name:	weird QQ.jpg‎
Views:	42
Size:	12.8 KB
ID:	5346  

  2. #2
    R purist
    Points: 35,103, Level: 100
    Level completed: 0%, Points required for next Level: 0
    TheEcologist's Avatar
    Location
    United States
    Posts
    1,921
    Thanks
    303
    Thanked 607 Times in 341 Posts

    Re: GLM diagnostic plots in r

    Quote Originally Posted by doy_h(r) View Post
    I am trying to fit a Gamma glm in R. getting very weird diagnostics even though all variables are significant. Please advise as to how i can improve this
    It would appear that there is a distinct group in your data, that you are not fitting. This can happen when you don't include all variables. Can you identify whether that cluster below conforms to any group?
    The true ideals of great philosophies always seem to get lost somewhere along the road..

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

    doy_h(r) (06-05-2015)

  4. #3
    Points: 316, Level: 6
    Level completed: 32%, Points required for next Level: 34

    Posts
    2
    Thanks
    2
    Thanked 0 Times in 0 Posts

    Re: GLM diagnostic plots in r

    Quote Originally Posted by TheEcologist View Post
    It would appear that there is a distinct group in your data, that you are not fitting. This can happen when you don't include all variables. Can you identify whether that cluster below conforms to any group?
    Thanks for your reply, it helps. I understand that there might be regional/geographical differences in the data. but how do i find that group ?

  5. #4
    R purist
    Points: 35,103, Level: 100
    Level completed: 0%, Points required for next Level: 0
    TheEcologist's Avatar
    Location
    United States
    Posts
    1,921
    Thanks
    303
    Thanked 607 Times in 341 Posts

    Re: GLM diagnostic plots in r


    Quote Originally Posted by doy_h(r) View Post
    Thanks for your reply, it helps. I understand that there might be regional/geographical differences in the data. but how do i find that group ?
    Add the residuals to your dataset (as a column), an then subset the data to residuals < -6. That should effectively isolate that group in the data, then hopefully you can find out what's up.

    You can extract the residuals with residuals(mymodel)
    The true ideals of great philosophies always seem to get lost somewhere along the road..

  6. The Following 2 Users Say Thank You to TheEcologist For This Useful Post:

    bugman (06-05-2015), doy_h(r) (10-04-2015)

+ 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