+ Reply to Thread
Results 1 to 3 of 3

Thread: Transforming interaction coefficients in odds ratio (logistic regression)

  1. #1
    Points: 27, Level: 1
    Level completed: 54%, Points required for next Level: 23

    Posts
    2
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Transforming interaction coefficients in odds ratio (logistic regression)




    Hello everyone.

    First of all, sorry for my english, I am not english mother tongue. Second, sorry for my stats knowledge, I'm not a statistician

    Could you please help me solve this problem?
    I have a logistic regression model and I want to interpret, in terms of odds ratios, the estimated coefficients of an interaction.
    I know that the transformation is not straightforward and that I have to make some calculations on my estimated coefficients before exponentiating to obtain odds ratios.

    My goal would be to learn how to do it not only in this particular case, but also in other models.

    I'll give you the values in the attached image (R output)

    I hope someone of you will be so kind to help me
    Attached Images  

  2. #2
    Omega Contributor
    Points: 38,253, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    6,989
    Thanks
    397
    Thanked 1,185 Times in 1,146 Posts

    Re: Transforming interaction coefficients in odds ratio (logistic regression)

    Quote Originally Posted by silviezza View Post
    I am not english mother tongue.
    That is fine as long as you use the international lanuage of smiley faces

    Can you provide the code used to generate this? Are the terms in the interactions continuous or categorical? What transformation do you need to make besides exponentiating beta coefficients from the logistic model.
    Stop cowardice, ban guns!

  3. #3
    Points: 27, Level: 1
    Level completed: 54%, Points required for next Level: 23

    Posts
    2
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Transforming interaction coefficients in odds ratio (logistic regression)


    Thanks for your reply!

    Well, I understand that when dealing with interactions you need to sum up betas of interaction with single coefficients before exponentiating... is that correct?
    The terms of interaction are both categorical, level of education attained and a dummy variable native born/foreigner

    This is the code:
    Attached Images  

+ 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