+ Reply to Thread
Results 1 to 2 of 2

Thread: Linear Regression Models

  1. #1
    Points: 2,570, Level: 30
    Level completed: 80%, Points required for next Level: 30

    Posts
    1
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Linear Regression Models




    I am being asksed if an equation is linear in the paramenters or variables and I am a bit lost. I understand that for something to be linear it cant be rasied to a power. But my question is if I have:
    e^B1+B2Xi+ui and
    lnYi=lnB1+B2 ln Xi+ui
    1 and 2 after the Bs are subscripts. Are these linear? How do you bring something down out of the power of e? Im not sure if Im even asking this the right way. If anyone can help, I'd appreciate it.
    I guess I dont understand if the ln or e make this linear.

  2. #2
    TS Contributor
    Points: 5,839, Level: 49
    Level completed: 45%, Points required for next Level: 111

    Location
    Nottingham
    Posts
    682
    Thanks
    0
    Thanked 27 Times in 27 Posts

    y=a+bx this linear in the parameters. y=a+bx^2 also linear in the parameters.
    log(y)=a+bx, this generalised linear since the y is not linear in the parameters but the log of y is.

+ Reply to Thread

           




Similar Threads

  1. Linear Mixed Models
    By danikoka in forum SPSS
    Replies: 2
    Last Post: 06-23-2010, 07:19 PM
  2. Linear Regression Models (2)
    By kingwinner in forum Regression Analysis
    Replies: 12
    Last Post: 05-22-2009, 04:35 PM
  3. Linear Regression Models (3)
    By kingwinner in forum Regression Analysis
    Replies: 4
    Last Post: 05-19-2009, 09:03 PM
  4. Linear Regression Models (1)
    By kingwinner in forum Regression Analysis
    Replies: 1
    Last Post: 05-19-2009, 09:02 PM
  5. Generalised Linear models
    By isaacalbeniz in forum Statistics
    Replies: 1
    Last Post: 07-24-2007, 04:19 AM

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