+ Reply to Thread
Results 1 to 2 of 2

Thread: Need assistance choosing the correct test for two nominal variables.

  1. #1
    Points: 5, Level: 1
    Level completed: 9%, Points required for next Level: 45

    Posts
    1
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Exclamation Need assistance choosing the correct test for two nominal variables.




    Hi!
    I have a single sample and asked them to think about their best and worst experiences in a class project. They answered identical sets of questions when considering the best project and again when considering the worst project.

    Here are the question examples: When thinking about your best project experience, how was the project evaluated? A) group grade only; B) group and individual grades; C) individual grade only. When thinking your worst project experience how was the project evaluated? A) group grade only; B) group and individual grades; C) individual grade only.

    What I need to do is compare the two responses to see if how students were evaluated influenced the perception of the project experience.

    I have run a chi square and the results are statistically significant but I am a little suspect of the results and want to make sure I am running the right test. I am also concerned that the category of individual grade only could be throwing off the results since it is a group project that is being graded although this one way they were graded but very few people selected this answer.

    Thank you for you time and assistance!!! It is greatly appreciated!!

  2. #2
    TS Contributor
    Points: 17,749, Level: 84
    Level completed: 80%, Points required for next Level: 101
    Karabiner's Avatar
    Location
    FC Schalke 04, Germany
    Posts
    2,540
    Thanks
    56
    Thanked 640 Times in 602 Posts

    Re: Need assistance choosing the correct test for two nominal variables.


    I have run a chi square and the results are statistically significant but I am a little suspect of the results and want to make sure I am running the right test.
    These are dependent measures. You compared 2 responses from the same subjects. Therefore you need a test for dependent samples. I don't know of a test which can handle more than 2 response options. McNemar's test, for example, can handle only 2 response options.

    With kind regards

    K.

+ Reply to Thread

           




Tags for this 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