+ Reply to Thread
Results 1 to 3 of 3

Thread: Testing the equality of the Residual Sum of Squares of two linear models

  1. #1
    Points: 3,910, Level: 39
    Level completed: 74%, Points required for next Level: 40

    Posts
    13
    Thanks
    1
    Thanked 0 Times in 0 Posts

    Testing the equality of the Residual Sum of Squares of two linear models




    I have two models of a dependent variable:

    Y = a1 + b1X1

    and

    Y = a2 + b2X2

    The variances around the lines of least error are important for my theory, and I wish to test if my two models have significantly different degrees of variance.

    How do I test this?

  2. #2
    Super Moderator
    Points: 13,151, Level: 74
    Level completed: 76%, Points required for next Level: 99
    Dragan's Avatar
    Location
    Illinois, US
    Posts
    2,014
    Thanks
    0
    Thanked 223 Times in 192 Posts

    Re: Testing the equality of the Residual Sum of Squares of two linear models

    I would suggest that you use the bootstrap. Briefly, you would take the error terms from each of your two regression models and create 95% bootstrap confidence intervals for the two variances for each of the two sets of the error terms. An easy way to address your query would be to look to see if the confidence intervals overlap (or not).

  3. #3
    Points: 3,910, Level: 39
    Level completed: 74%, Points required for next Level: 40

    Posts
    13
    Thanks
    1
    Thanked 0 Times in 0 Posts

    Re: Testing the equality of the Residual Sum of Squares of two linear models


    Thank you Dragan. Suppose I found that these intervals do not overlap when using the 95% confidence interval, how would my conclusion incorporate this value of 95%? Could I state that there is 5% risk the variances are identical?

+ 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