+ Reply to Thread
Results 1 to 8 of 8

Thread: Problem with residual?

  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

    Problem with residual?




    I don't know if this is an issue or not. There are the strange bars on the top and bottom of the residuals - I have never seen anything like this and can't imagine substantively what would cause it. My DV here is hours worked which is not going to be more than 40 or less than 0 normally.
    Attached Images  
    "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: 38,303, 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: Problem with residual?

    Is your outcome whole hours as integers and can some individuals have restrictions. What is the IV?
    Stop cowardice, ban guns!

  3. #3
    Devorador de queso
    Points: 95,705, Level: 100
    Level completed: 0%, Points required for next Level: 0
    Awards:
    Posting AwardCommunity AwardDiscussion EnderFrequent Poster
    Dason's Avatar
    Location
    Tampa, FL
    Posts
    12,931
    Thanks
    307
    Thanked 2,629 Times in 2,245 Posts

    Re: Problem with residual?

    This isn't unusual to see when the DV is discrete.
    I don't have emotions and sometimes that makes me very sad.

  4. #4
    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: Problem with residual?

    My out come is whole hours. No customer has more than 40 hours and very few have negative hours. There are a wide range of predictors some interval and some dummy variables. I am guessing this is caused by range restrictions on the DV.
    "Very few theories have been abandoned because they were found to be invalid on the basis of empirical evidence...." Spanos, 1995

  5. #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: Problem with residual?

    Quote Originally Posted by Dason View Post
    This isn't unusual to see when the DV is discrete.
    It has about 40 different levels.

    I guess my next question, since I have not seen this addressed, is this a serious issue for the standard errors. I have about 11000 data points if that matters....
    "Very few theories have been abandoned because they were found to be invalid on the basis of empirical evidence...." Spanos, 1995

  6. #6
    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: Problem with residual?

    You are probably fine like normal, but is there a slight negative trend in these residuals? So they are not some IID.


    Well I always thought concerns now come in regards to how you interpret coefficients that say with variable X, y-hat increases 4.65434. Are you fine with decimals in the face of using integers. Most times it is just a round procedure needed - I would guess?
    Stop cowardice, ban guns!

  7. #7
    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: Problem with residual?

    That is a good point about interpretation of the slopes when you have data that can't be subdivided. Is it reasonable to say an increase in 4.6 hours when in fact you can only work whole hours? I actually never considered that before... I honestly don't know if it is legitimate to talk about the data that way. Or whether rounding solves the problem.

    Sometimes it is painful to come to this board Makes me think to much.
    "Very few theories have been abandoned because they were found to be invalid on the basis of empirical evidence...." Spanos, 1995

  8. #8
    TS Contributor
    Points: 40,089, Level: 100
    Level completed: 0%, Points required for next Level: 0
    Awards:
    Downloads
    gianmarco's Avatar
    Location
    Italy
    Posts
    1,367
    Thanks
    232
    Thanked 301 Times in 225 Posts

    Re: Problem with residual?


    As to your question about the bars, they could actually correspond to +\- 2SD.
    http://cainarchaeology.weebly.com/

  9. The Following User Says Thank You to gianmarco For This Useful Post:

    noetsi (03-29-2016)

+ 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