+ Reply to Thread
Results 1 to 3 of 3

Thread: Question Regarding Research Design

  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

    Question Regarding Research Design




    If I have a dataset with 100 unspecified cases and I know from a previous chart review that the likelihood is that 10% of these are indeed cases how do I randomly select the 10%? I have been searching for journal articles that describe a method but have been unsuccessful. I would greatly appreciate any advice or direction to a journal article. Thanks!

  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: Question Regarding Research Design

    100 random observations, don't know if the observation(s) is a case or not? The prevalence of cases is 10% in population, so if your sample is random, 10% of your observations should be cases.


    I don't get the rest of your post, why would you randomly select these 10%? Seems pretty Bayesian...


    Please provide more information!!
    Stop cowardice, ban guns!

  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

    Re: Question Regarding Research Design


    I completed a review of a few hundred medical charts and identified that 10% of the time when an unspecified ICD code was recorded, the presentation could be attributed to a bee sting. I now want to use this result and extrapolate (I'm not sure if that is the right term) 10% of unspecified presentations from a larger national data set (3000 presentations). Ultimately I am investigating trends over time but I can't include all unspecified presentations in my analysis as it is most likely that only 10% of these are due to bee sting for example.

    I would appreciate any advice. After further investigation I think I have to calculate weighted averages but I'm not sure. Thanks for your help!

+ 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