+ Reply to Thread
Results 1 to 7 of 7

Thread: P-value for a regression where expected slope is 1:1

  1. #1
    Points: 57, Level: 1
    Level completed: 14%, Points required for next Level: 43

    Posts
    4
    Thanks
    0
    Thanked 0 Times in 0 Posts

    P-value for a regression where expected slope is 1:1




    Hi, I am comparing two values for vegetation cover from two time periods. The expected value is y=x for the slope. I am curious how to calculate a p-value for this since the standard regression software is comparing the slope to zero, right? I could subtract the pre from the post, but then what would I put on the x-axis?

    Thank you so much for your help!

  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: P-value for a regression where expected slope is 1:1

    So they have a perfect correlated relationship? Provide some more info please. If you want to compare a value to something other than 0 you just need to write a estimate statement. I believe its just like doing a one-sample ttest.
    Stop cowardice, ban guns!

  3. #3
    Points: 57, Level: 1
    Level completed: 14%, Points required for next Level: 43

    Posts
    4
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: P-value for a regression where expected slope is 1:1

    Quote Originally Posted by hlsmith View Post
    So they have a perfect correlated relationship? Provide some more info please. If you want to compare a value to something other than 0 you just need to write an estimate statement. I believe its just like doing a one-sample ttest.
    Thank you for the response! My do not have an exact 1:1 relationship, but that would be the expected relationship given no change in other variables. Is there a way to write and estimate statement in Minitab? I tried to google it and was a little confused. I apologize, I am a student and still really shaky with my understanding of statistics and ability to speak the language. I sincerely appreciate the help though!

  4. #4
    TS Contributor
    Points: 18,889, Level: 87
    Level completed: 8%, Points required for next Level: 461
    CowboyBear's Avatar
    Location
    New Zealand
    Posts
    2,062
    Thanks
    121
    Thanked 427 Times in 328 Posts

    Re: P-value for a regression where expected slope is 1:1

    Do you mean that you want to test a null hypothesis that the slope is exactly one? If so you can calculate the t-test statistic as (estimated slope - 1)/SE rather than (estimated slope/SE).
    Matt aka CB | twitter.com/matthewmatix

  5. The Following User Says Thank You to CowboyBear For This Useful Post:

    hlsmith (11-23-2016)

  6. #5
    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: P-value for a regression where expected slope is 1:1

    Right on CB, glad to see I am finally figuring this stuff out after inundating myself.

    What about a -1 slope or how are you planning to interpret the result (two-tailed)?
    Stop cowardice, ban guns!

  7. #6
    TS Contributor
    Points: 18,889, Level: 87
    Level completed: 8%, Points required for next Level: 461
    CowboyBear's Avatar
    Location
    New Zealand
    Posts
    2,062
    Thanks
    121
    Thanked 427 Times in 328 Posts

    Re: P-value for a regression where expected slope is 1:1

    Matt aka CB | twitter.com/matthewmatix

  8. #7
    Points: 57, Level: 1
    Level completed: 14%, Points required for next Level: 43

    Posts
    4
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: P-value for a regression where expected slope is 1:1


    Quote Originally Posted by CowboyBear View Post
    Do you mean that you want to test a null hypothesis that the slope is exactly one? If so you can calculate the t-test statistic as (estimated slope - 1)/SE rather than (estimated slope/SE).
    Thank you!

+ 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