+ Reply to Thread
Results 1 to 6 of 6

Thread: Sample size help!!

  1. #1
    Points: 17, Level: 1
    Level completed: 33%, Points required for next Level: 33

    Posts
    2
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Sample size help!!




    Hello! New to the forum but would greatly appreciate any help people may have to offer... Essentially I am trying to organise a scientific study looking achillies tendon rupture. Specifically, I am looking to prove that calf strength never returns to that of the uninjured side, regardless of treatment modality. I plan on bringing patients back to clinic, and measure the calf muscle strength in both the injured and uninjured leg using an isometric dynamometer. Trouble is I have absolutely no idea where to start when calculating the required sample size for such a project. I have done a search and much of it goes over my head. So does anyone have any information for a relative novice as to where to begin?? I would be sooooo greatful. Thanks in advance... Alex

  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: Sample size help!!

    So you have an acute rupture, surgical intervention, then bring them in back in to measure strength strength in both lower legs.

    How do you address the lack of asymmetry in strength that may have existed prior to injury. Will everyone come back into the clinic at the same time post surgical intervention? How do you control for activity and training per patient post surgical intervention?
    Stop cowardice, ban guns!

  3. #3
    Points: 1,023, Level: 17
    Level completed: 23%, Points required for next Level: 77
    Khrisstian's Avatar
    Posts
    35
    Thanks
    3
    Thanked 2 Times in 2 Posts

    Re: Sample size help!!

    If you're trying to prove something, that's called persuasion. In science, you're trying to find the truth.

    What's your null hypothesis and what is your alternative hypothesis?

    What is the population you are studying?

  4. #4
    Points: 17, Level: 1
    Level completed: 33%, Points required for next Level: 33

    Posts
    2
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Sample size help!!

    Thanks for the replies everyone. There will be two groups of patients- those patients managed operatively and non operatively. I want to identify patients at 6 months, 1 year and 2 years from the time of injury/repair. At that point I'm going to bring them back to measure calf diameter and plantarflexion strength, in addition to performing foot and ankle scores and satisfaction questionnaires. The null hypothesis will be there is no difference between those ruptures managed surgically and those managed non operatively. Also that calf strength never returns to full strength regardless of treatment modality.
    The point you raise regarding the asymmetry in calf strength is a good one, as studies have shown most people do have a 'dominant' calf muscle- usually not related hand dominance. We can't control for this. Both groups undergo functional rehabilitation exercises under the careful guidance of the physiotherapy team. Admittedly some will be more compliant than others, which will be another limitation of the study.
    This will be done at a University teaching hospital, which serves a population of approximately 400,000.
    What other information do I need in working out the required smaple size? So confused

  5. #5
    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: Sample size help!!

    You are probably not randomizing the treatment options, so the study will be limited by confounding by indication.

    Your sample size is based on your primary endpoint/measure. Which variable do you care about the most. Then how is the variable formatted (categorical, continuous, ordinal), and do you just want to compare a certain endpoint time or multiple endpoints. Next you use the best information available to you to postulate what may be the smallest treatment effect you may see and how dispersed will those values be. Given you know there will be two treatment groups and what variable you want to compare - then which test you want to conduct will be easy to get at. Lastly, you just look up the appropriate sample size test for the statistical test you will be conducting and plug in your postulated data.

    Please, keep asking questons if you need to!
    Stop cowardice, ban guns!

  6. #6
    Fortran must die
    Points: 58,790, Level: 100
    Level completed: 0%, Points required for next Level: 0
    noetsi's Avatar
    Posts
    6,532
    Thanks
    692
    Thanked 915 Times in 874 Posts

    Re: Sample size help!!


    In science, you're trying to find the truth.
    I have to respectfully disagree with that statement. First, because I don't think one can even discuss "truth" in research where reality is unknowable (for many reasons including uncertainty and measurement error). What scientist believe is correct may or may not be the same as reality and the latter is almost certainly beyond our capacity to determine.

    Second, because if one reads academic journals, or follows the history of scientific research its pretty obvious that scientist are not value neutral observers. Many argue this is not actual possible (post-positivist for example) and their arguments are pretty convincing to me.

    But this departs from the OP interest in any case
    "Very few theories have been abandoned because they were found to be invalid on the basis of empirical evidence...." Spanos, 1995

+ 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