+ Reply to Thread
Results 1 to 4 of 4

Thread: Logit:why aren't my exponentiated coefficients equaling my odds ratio (for nominal x)

  1. #1
    Points: 7, Level: 1
    Level completed: 13%, Points required for next Level: 43

    Posts
    2
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Logit:why aren't my exponentiated coefficients equaling my odds ratio (for nominal x)




    I'm running logit in JMP. My understanding is that if you exponentiate the coefficients, you get the change in odds ratios from a 1 unit change in X.

    This works perfectly for continuous independent variables, but not for nominal (0,1) independent variables. Example below:

    For parameter estimates I'm getting:

    Term Estimate Intercept -1.516621
    Gender[Female] 0.22189387

    Level1 /Level2 Odds Ratio
    Male Female 0.6416016
    Female Male 1.5585996

    Shouldn't my odds ratio for males be exp(-1.516621)=0.220486 and for females be exp(0.20461503)=1.2270525?

    Befuddled by this. Would really appreciate some help. Thanks!

  2. #2
    TS Contributor
    Points: 12,227, Level: 72
    Level completed: 45%, Points required for next Level: 223
    rogojel's Avatar
    Location
    I work in Europe, live in Hungary
    Posts
    1,470
    Thanks
    160
    Thanked 332 Times in 312 Posts

    Re: Logit:why aren't my exponentiated coefficients equaling my odds ratio (for nomina

    hi,
    there is no such thing as an odds ratio for males and one for females, you have only the odds ratio of changing from male to female (or viceversa) as given in the output of the program. The intercept plays no role in the odds ratio calculation BTW.

    Still, the numbers do not match, dont you have some interaction term in the model ?

    regards

  3. #3
    Points: 7, Level: 1
    Level completed: 13%, Points required for next Level: 43

    Posts
    2
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Arrow Re: Logit:why aren't my exponentiated coefficients equaling my odds ratio (for nomina

    Thank you rogojel for correcting my misuse of Odds Ratio vs. Odds. I see that you are correct.

    There are no interaction terms in the model. It's just buy (0/1) as a function of gender. That's it.

    Interestingly I ran the same dataset through SPSS for windows. It gives me different coefficients, and the math seems to work with those.

    JMP SPSS (can't get formatting right here, but first number is JMP, second SPSS)
    Intercept -1.516621 -1.739
    Gender(F) 0.22189387 0.444

    Both programs report the odds ratio/exponentiated gender coefficient as 1.559.

    It looks to me that JMP is showing the wrong coefficients though.

    I don't know... will have to have to try and get someone at SAS JMP I guess to look at this.

    UPDATE: Per the SAS JMP forum apparently you have to make the gender variable ordinal and not nominal to get the right output. I find this confusing, especially since the odds ratio shows as the same either way, but the coefficients seem to be "wrong" when using nominal.
    Last edited by Chriscic; 11-28-2015 at 09:34 PM.

  4. #4
    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: Logit:why aren't my exponentiated coefficients equaling my odds ratio (for nomina


    Yo, not on a computer or havenot read all of your post, but SAS has a weird quark. See a prior thread on here that I posted. Sometimes it has to do with the paramour option.

+ 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