+ Reply to Thread
Results 1 to 4 of 4

Thread: Assuming there is a normal distribution and not assuming so

  1. #1
    Points: 1,259, Level: 19
    Level completed: 59%, Points required for next Level: 41

    Posts
    6
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Assuming there is a normal distribution and not assuming so




    Hi, I have a problem which I don't really understand.

    I have 2 sets of data, which have been gotten from 2 different methods of testing something.

    The data is in this case:
    1 2 3 4 5 6 7 8
    Method A: 212 180 197 204 219 258 206 200
    Method B: 225 187 195 209 225 260 207 210

    So, the ideal case would have been that the values for 1 were the same for both methods, the values for 2 were the same, etc.

    Now, what I need to do is test for a difference between the 2 methods, both with and without assumption of a normal distribution, and as it turns out, I am quite clueless. If anyone could do some sort of walk-through on how to solve this, or atleast point me in the right direction, I would be most grateful.

  2. #2
    Points: 1,686, Level: 23
    Level completed: 86%, Points required for next Level: 14

    Posts
    67
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Assuming there is a normal distribution and not assuming so

    Does the Method A and Method B are applied to the same subjects?

  3. #3
    Points: 1,259, Level: 19
    Level completed: 59%, Points required for next Level: 41

    Posts
    6
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Assuming there is a normal distribution and not assuming so

    Yes, they are.

  4. #4
    Points: 1,686, Level: 23
    Level completed: 86%, Points required for next Level: 14

    Posts
    67
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Assuming there is a normal distribution and not assuming so


    If you are concerned with the difference between means between these two methods, you can use a paired t test assuming a normal distribution. When you assume that it is not a normal distribution, you can use a Wilcoxon signed ranks test.

    You can find whether the distribution is normal or non gaussian by running a normality test in spss or any other advanced statistical package.

    Hope this helps.

+ Reply to Thread

           




Similar Threads

  1. Replies: 2
    Last Post: 05-11-2011, 02:35 PM
  2. Replies: 1
    Last Post: 11-11-2010, 10:56 PM
  3. Replies: 0
    Last Post: 01-23-2008, 11:32 PM
  4. Replies: 2
    Last Post: 08-19-2007, 11:54 PM
  5. Assuming Normal distribution
    By kirpa_karo@hotmail.com in forum Statistics
    Replies: 1
    Last Post: 08-02-2006, 11:29 PM

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