Notices
Results 1 to 8 of 8

Thread: Which Significnce Tsting Method to Use

  1. #1 Which Significnce Tsting Method to Use 
    New Member
    Join Date
    Mar 2014
    Posts
    4
    Hi, I am pretty new to statistical significance testin. I understand each of the two groups of data must be of uniform distribution to carry out the t tests. So what happens if one group is uniform and the other isn't? Do I use non-parametric test or can I still use the t test?


    Thank you


    Reply With Quote  
     

  2.  
     

  3. #2  
    Moderator Moderator Cogito Ergo Sum's Avatar
    Join Date
    Jun 2013
    Location
    Belgium
    Posts
    2,519
    Quote Originally Posted by oludot5 View Post
    Hi, I am pretty new to statistical significance testin. I understand each of the two groups of data must be of uniform distribution to carry out the t tests. So what happens if one group is uniform and the other isn't? Do I use non-parametric test or can I still use the t test?


    Thank you

    It is advisable to use the non-parametric variant of the Student t-test.


    "The only safe rule is to dispute only with those of your acquaintance of whom you know that they possess sufficient intelligence and self-respect not to advance absurdities; to appeal to reason and not to authority, and to listen to reason and yield to it; and, finally, to be willing to accept reason even from an opponent, and to be just enough to bear being proved to be in the wrong."

    ~ Arthur Schopenhauer, The Art of Being Right: 38 Ways to Win an Argument (1831), Stratagem XXXVIII.
    Reply With Quote  
     

  4. #3  
    New Member
    Join Date
    Mar 2014
    Posts
    4
    Hi Cognito,

    THanks for your reply. In this case, where I m trying to carry out significance test between two groups with one having a normal distribution and the other not normal, are you saying I should use a non parametric test like Mann-Whitney test?
    Reply With Quote  
     

  5. #4  
    Moderator Moderator Cogito Ergo Sum's Avatar
    Join Date
    Jun 2013
    Location
    Belgium
    Posts
    2,519
    Quote Originally Posted by oludot5 View Post
    Hi Cognito,

    THanks for your reply. In this case, where I m trying to carry out significance test between two groups with one having a normal distribution and the other not normal, are you saying I should use a non parametric test like Mann-Whitney test?

    If your groups are unpaired, then you have to use a Mann-Whitney test (or a Wilcoxon rank-sum test).
    I hope this helps.
    "The only safe rule is to dispute only with those of your acquaintance of whom you know that they possess sufficient intelligence and self-respect not to advance absurdities; to appeal to reason and not to authority, and to listen to reason and yield to it; and, finally, to be willing to accept reason even from an opponent, and to be just enough to bear being proved to be in the wrong."

    ~ Arthur Schopenhauer, The Art of Being Right: 38 Ways to Win an Argument (1831), Stratagem XXXVIII.
    Reply With Quote  
     

  6. #5  
    New Member
    Join Date
    Mar 2014
    Posts
    4
    Thanks Cognito.


    My sample size is 19 and they are paired data. What is the best test to use in this case?
    Reply With Quote  
     

  7. #6  
    Moderator Moderator Cogito Ergo Sum's Avatar
    Join Date
    Jun 2013
    Location
    Belgium
    Posts
    2,519
    Quote Originally Posted by oludot5 View Post
    Thanks Cognito.


    My sample size is 19 and they are paired data. What is the best test to use in this case?

    A Wilcoxon signed rank-sum test (not the Mann-Whitney test, because that is the non-parametric variant of the paired Student t-test).
    "The only safe rule is to dispute only with those of your acquaintance of whom you know that they possess sufficient intelligence and self-respect not to advance absurdities; to appeal to reason and not to authority, and to listen to reason and yield to it; and, finally, to be willing to accept reason even from an opponent, and to be just enough to bear being proved to be in the wrong."

    ~ Arthur Schopenhauer, The Art of Being Right: 38 Ways to Win an Argument (1831), Stratagem XXXVIII.
    Reply With Quote  
     

  8. #7  
    New Member
    Join Date
    Mar 2014
    Posts
    4
    thanks a lot, appreciate
    Reply With Quote  
     

  9. #8  
    Moderator Moderator Cogito Ergo Sum's Avatar
    Join Date
    Jun 2013
    Location
    Belgium
    Posts
    2,519
    Quote Originally Posted by oludot5 View Post
    thanks a lot, appreciate

    You are welcome.
    If you have more questions, feel free to ask them.
    "The only safe rule is to dispute only with those of your acquaintance of whom you know that they possess sufficient intelligence and self-respect not to advance absurdities; to appeal to reason and not to authority, and to listen to reason and yield to it; and, finally, to be willing to accept reason even from an opponent, and to be just enough to bear being proved to be in the wrong."

    ~ Arthur Schopenhauer, The Art of Being Right: 38 Ways to Win an Argument (1831), Stratagem XXXVIII.
    Reply With Quote  
     

Similar Threads

  1. Replies: 2
    Last Post: January 11th, 2014, 12:49 PM
  2. Macauley method
    By Karel007 in forum Mechanical, Structural and Chemical Engineering
    Replies: 0
    Last Post: June 7th, 2012, 03:46 AM
  3. Transit method
    By PetTastic in forum Astronomy & Cosmology
    Replies: 6
    Last Post: January 20th, 2012, 07:52 PM
  4. Method of complements
    By bit4bit in forum Mathematics
    Replies: 1
    Last Post: September 20th, 2008, 12:35 PM
  5. Scientific method
    By Cuntinuum in forum General Discussion
    Replies: 6
    Last Post: January 31st, 2008, 03:20 PM
Bookmarks
Bookmarks
Posting Permissions
  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •