+ Reply to Thread
Results 1 to 2 of 2

Thread: Weighting adjusted rates

  1. #1
    Points: 69, Level: 1
    Level completed: 38%, Points required for next Level: 31

    Posts
    5
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Weighting adjusted rates




    Hi All,

    I have a patient database with columns for observed and expected values for a number of outcomes. The observed values are binary, expected values came from predicting probabilities after carrying out logistic regression. Now, to calculate a risk-adjusted rate for an outcome I can do :

    sum(Observed)/sum(Expected)

    However, I know that each patient has spent a proportion of their time (total hospital stay) in one or several of 10 wards. I have columns for prop_wardA...prop_wardJ to tell me the proportions of time spent in each ward.

    Is there a way I can use this information, along with the above equation, to get a weighted adjusted rate for each ward, reflecting the time patients spent on each ward?

    Thanks for your help

  2. #2
    Points: 69, Level: 1
    Level completed: 38%, Points required for next Level: 31

    Posts
    5
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Weighting adjusted rates


    I was thinking something like:

    sum(observed)/sum(expected) x sum(prop_wardA)/sum(LOS)

    where LOS is total length of stay. Does this work when you sum over all patients though?

+ 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