+ Reply to Thread
Results 1 to 4 of 4

Thread: Test for healthy and sick organ development

  1. #1
    Points: 1,448, Level: 21
    Level completed: 48%, Points required for next Level: 52

    Posts
    11
    Thanks
    1
    Thanked 0 Times in 0 Posts

    Test for healthy and sick organ development




    Hi guys,

    Quick question: I have data from patients who suffer on some organ failure. Letís say I have ten organ function measurements over time. Based on some idea I also use information from this patient and simulate a healthy organ development (how is not important right now) Hence, I have the same patient with two samples, one sample is the real measured organ failure and the second is a simulated sample were we assume healthy organ development. What is an appropriate statistical test to check whether there is a significant difference between the sick and the healthy sample? T-test or Welch test?

    Many thanks in advance.

  2. #2
    Omega Contributor
    Points: 38,253, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    6,989
    Thanks
    397
    Thanked 1,185 Times in 1,146 Posts

    Re: Test for healthy and sick organ development

    So one is failure and one is development? This seems conflicting. You have how many patients?

  3. #3
    Points: 1,448, Level: 21
    Level completed: 48%, Points required for next Level: 52

    Posts
    11
    Thanks
    1
    Thanked 0 Times in 0 Posts

    Re: Test for healthy and sick organ development

    My problem is more related to the assumptions of theses test, which I never understood. I know you probably explained this 472 thousand times in this forum and it is written in every textbook but I don’t get it.

    Let say I can describe the healthy and the sick sample by linear regression, then a test would compare the slopes? What is the population then, all slopes? Are the estimated slopes independent? It is actually well-known that these kind of slopes are log-normal distributed, so one assumption of the test is already violated. Do I have to transform the slopes to normal?

  4. #4
    Omega Contributor
    Points: 38,253, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    6,989
    Thanks
    397
    Thanked 1,185 Times in 1,146 Posts

    Re: Test for healthy and sick organ development


    I don't know if I should still ignore your first post, which confused me. What procedure do you want to run and are you just trying to compare two groups values for a log normal variable?

    Thanks.
    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