+ Reply to Thread
Results 1 to 4 of 4

Thread: Basic Sample Size Question

  1. #1
    Points: 239, Level: 4
    Level completed: 78%, Points required for next Level: 11

    Posts
    3
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Basic Sample Size Question




    hello this is my first thread, i want to ask something,
    example: i want to to know the association between cholesterol level (categorized as extreme ,high, normal, low) and liver cirrhosis (categorized as class A, B, and C), what formulas should i use to determine the sample size?

    should i use the categorical independent formula? if so, how do i determine the P1 and P2 value?

    or is it better to use uncategorized cholesterol level and use numerical sample size?

    Thank you

  2. #2
    Points: 5,083, Level: 45
    Level completed: 67%, Points required for next Level: 67

    Posts
    109
    Thanks
    19
    Thanked 3 Times in 3 Posts

    Re: Basic Sample Size Question

    All else being equal it is better to use uncategorised data if possible. You lose some information whenever you categorise a continuous variable: for instance if you had a cholesterol of 2.1 and another of 4.9 you might categorise both as normal, but you have lost the information that there is a difference of 2.8 between them.

  3. #3
    Omega Contributor
    Points: 38,284, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    6,991
    Thanks
    397
    Thanked 1,185 Times in 1,146 Posts

    Re: Basic Sample Size Question

    what type of association? what test are you planning on performing and what is your hypothesis?
    Stop cowardice, ban guns!

  4. #4
    Points: 239, Level: 4
    Level completed: 78%, Points required for next Level: 11

    Posts
    3
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Basic Sample Size Question


    Quote Originally Posted by Prometheus View Post
    All else being equal it is better to use uncategorised data if possible. You lose some information whenever you categorise a continuous variable: for instance if you had a cholesterol of 2.1 and another of 4.9 you might categorise both as normal, but you have lost the information that there is a difference of 2.8 between them.
    thank you very much

    Quote Originally Posted by hlsmith View Post
    what type of association? what test are you planning on performing and what is your hypothesis?
    umm, the association is higher level of cirrhosis is associated with lower level of cholesterol.
    i'm planning to use chi-square, is it a right choice?
    my hypotheses is higher level of cirrhosis is significantly decrease cholesterol level.

+ 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