+ Reply to Thread
Results 1 to 7 of 7

Thread: Interpreting Odds Ratios... weird question

  1. #1
    Points: 132, Level: 2
    Level completed: 64%, Points required for next Level: 18

    Posts
    2
    Thanks
    3
    Thanked 0 Times in 0 Posts

    Red face Interpreting Odds Ratios... weird question




    Hi,

    I sort of have a weird question. I have a basic understanding of ORs, and can interpret them, but it's never been clear to me why we interpret values above/below 1 as percents and values 2+/- as x times. Let me be clearer. Let's say we're talking about the association of diabetes with glycemic control.

    I might have an OR = 1.2, or an OR =4.0.

    In the first OR, I would say diabetics are 20% more likely to achieve glycemic control. In the second OR, I would say 4 times more likely to achieve glycemic control. So, back to my question, why do we say % in the former, but x times in the latter?

    Thanks in advance!

  2. #2
    Omega Contributor
    Points: 38,396, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    7,001
    Thanks
    398
    Thanked 1,186 Times in 1,147 Posts

    Re: Interpreting Odds Ratios... weird question

    Its just to mislead the uneducated reader, since 8% greater odds for outcome sounds better than 1.08 times greater odds. Just kidding, but not totally.


    It is just an etiquette thing. Actually you can do whichever you want, but most adhere to what you presented.
    Stop cowardice, ban guns!

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

    Ceci18 (02-06-2017)

  4. #3
    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: Interpreting Odds Ratios... weird question

    What seems to me a bit more questionable is the use of the term "likely". Strictly we have a 20% increase in the odds, so I guess the explanation "20% more likely" might be misleading .

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

    Ceci18 (02-06-2017)

  6. #4
    Omega Contributor
    Points: 38,396, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    7,001
    Thanks
    398
    Thanked 1,186 Times in 1,147 Posts

    Re: Interpreting Odds Ratios... weird question

    Yeah, I have a boilerplate phrasing I always use, even though some people like to say more likely, I stay away from it many because is it appropriate, maybe/maybe not?


    Then you get to the more nuanced statements where you say, males had a 2 times greater ADJUSTED odds of Y than females. People need to use that term more often if it was taken from a multiple regression model, and if multiple different models were used they need to say what was controlled for in particular.
    Stop cowardice, ban guns!

  7. The Following User Says Thank You to hlsmith For This Useful Post:

    Ceci18 (02-06-2017)

  8. #5
    Points: 132, Level: 2
    Level completed: 64%, Points required for next Level: 18

    Posts
    2
    Thanks
    3
    Thanked 0 Times in 0 Posts

    Re: Interpreting Odds Ratios... weird question

    Thank you, both, for your answers! I suppose I should be sticking to the "official" interpretation by using "odds of" instead of the likely language. Maybe that would have spared my confusion with the % vs. x. Thanks again and happy holidays!

  9. #6
    Points: 5,407, Level: 47
    Level completed: 29%, Points required for next Level: 143

    Posts
    46
    Thanks
    29
    Thanked 1 Time in 1 Post

    Re: Interpreting Odds Ratios... weird question

    What I find even more interesting is that with odds ratio/relative risk/hazard ratio of 1.2 one can conclude that first group has 20% increased risk of something, but also that the second group has 16.66% reduced risk of something (because 1/1.2=0.8333). It is just shown reciprocally

  10. #7
    Omega Contributor
    Points: 38,396, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    7,001
    Thanks
    398
    Thanked 1,186 Times in 1,147 Posts

    Re: Interpreting Odds Ratios... weird question


    I believe invertibility holds with hazard ratios and odds ratios, but not with relative risks.


    But, yes it is a nice property!!
    Stop cowardice, ban guns!

+ 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