+ Reply to Thread
Results 1 to 5 of 5

Thread: Can you include X1/X2 in a model when you've already included X1 and X2?

  1. #1
    Points: 58, Level: 1
    Level completed: 16%, Points required for next Level: 42

    Posts
    7
    Thanks
    3
    Thanked 0 Times in 0 Posts

    Can you include X1/X2 in a model when you've already included X1 and X2?




    Can you include X1/X2 in a model when you've already included X1 and X2? For example, I am trying to predict housing prices. X1=square feet and X2=lot size. I want to see how much of the lot isn't being used as a proxy for how big the front and back yard are. Thus, I want to use X1/X2 since this is my only data. Can I include X1/X2 when I have already included X1 and X2?

  2. #2
    Cookie Scientist
    Points: 13,431, Level: 75
    Level completed: 46%, Points required for next Level: 219
    Jake's Avatar
    Location
    Austin, TX
    Posts
    1,293
    Thanks
    66
    Thanked 584 Times in 438 Posts

    Re: Can you include X1/X2 in a model when you've already included X1 and X2?

    Yes. It's not that different from an interaction term.
    “In God we trust. All others must bring data.”
    ~W. Edwards Deming

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

    smw10c (04-11-2017)

  4. #3
    Points: 58, Level: 1
    Level completed: 16%, Points required for next Level: 42

    Posts
    7
    Thanks
    3
    Thanked 0 Times in 0 Posts

    Re: Can you include X1/X2 in a model when you've already included X1 and X2?

    Quote Originally Posted by Jake View Post
    Yes. It's not that different from an interaction term.
    Thank you. Quick question: Let's say you have the following output:

    HousePrice=150,000+20Square_feet+5Lot_size-7Square_feet/Lot_size

    Let's say you want to predict the effect on house price of an increase in square feet of 100. For "-7Square_feet/Lot_size" would you divide 100 by the average lot size? If not, how would you predict the change in house price?

  5. #4
    Cookie Scientist
    Points: 13,431, Level: 75
    Level completed: 46%, Points required for next Level: 219
    Jake's Avatar
    Location
    Austin, TX
    Posts
    1,293
    Thanks
    66
    Thanked 584 Times in 438 Posts

    Re: Can you include X1/X2 in a model when you've already included X1 and X2?

    Just like in models with an interaction term, in this situation you can plug in any value of lot_size that you're interested in. The sample mean of lot_size is a very common and reasonable choice. But there may be other values of lot_size that are of a priori interest as well.
    “In God we trust. All others must bring data.”
    ~W. Edwards Deming

  6. The Following User Says Thank You to Jake For This Useful Post:

    smw10c (04-11-2017)

  7. #5
    Points: 58, Level: 1
    Level completed: 16%, Points required for next Level: 42

    Posts
    7
    Thanks
    3
    Thanked 0 Times in 0 Posts

    Re: Can you include X1/X2 in a model when you've already included X1 and X2?


    Quote Originally Posted by Jake View Post
    Just like in models with an interaction term, in this situation you can plug in any value of lot_size that you're interested in. The sample mean of lot_size is a very common and reasonable choice. But there may be other values of lot_size that are of a priori interest as well.
    Thank you so much!

+ 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