+ Reply to Thread
Results 1 to 2 of 2

Thread: How to compare whether younger patients have better therapeutic results ?

  1. #1
    Points: 2,493, Level: 30
    Level completed: 29%, Points required for next Level: 107

    Posts
    5
    Thanks
    1
    Thanked 0 Times in 0 Posts

    How to compare whether younger patients have better therapeutic results ?




    Hi, I've just finished a research on 30 patients. Age range was 26 to 80. I've tested everyone of them before and after the treatment. Results are expressed as numerical variables.
    Now I want to see whether younger patients have reached better therapeutic results than older. Which test would you recommend ?

    Thank you very much.

  2. #2
    Points: 2,462, Level: 30
    Level completed: 8%, Points required for next Level: 138

    Posts
    200
    Thanks
    20
    Thanked 48 Times in 43 Posts

    Re: How to compare whether younger patients have better therapeutic results ?


    Hi, what you can do is a mixed regression model: The test scores Y are the outcome, the age is a continuous predictor, before / after (lets name this X) is a categorical predictor. And finally you have to include ID as a random effect (since you have a repeated measurement design). If the interaction term between age and X is significant, this means that the dependency of Y on age shows a different slope before versus after the treatment. I think this is what you want, because this tells you if the difference between the Y level before and after the treatment depends on age, am I right?

    In R the code could look like this:

    library(nlme)
    model <- lme(data=data,Y ~ age + X + age:X, random=~(1|ID))
    summary(model)

    and the significance of age:X is what you are interested in.
    Last edited by mmercker; 12-21-2015 at 01:48 AM.

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

    nicck (01-08-2016)

+ 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