+ Reply to Thread
Results 1 to 6 of 6

Thread: Significance test for two proportions using SPSS

  1. #1
    Points: 26, Level: 1
    Level completed: 52%, Points required for next Level: 24

    Posts
    6
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Significance test for two proportions using SPSS




    Hi,

    I have a binary data set which I have calculated proportions for and would like to compare and test 2 proportions for a significant difference. I'm a little confused as to what test would be appropriate for me to use in this scenario / how to interpret the output.
    Any help would be massively appreciated.
    Thank you.

  2. #2
    TS Contributor
    Points: 17,742, Level: 84
    Level completed: 79%, Points required for next Level: 108
    Karabiner's Avatar
    Location
    FC Schalke 04, Germany
    Posts
    2,539
    Thanks
    56
    Thanked 639 Times in 601 Posts

    Re: Significance test for two proportions using SPSS

    If you want to compare binary measures from the same sample,
    then McNemar's test comes into mind.

    With kind regards

    K.

  3. #3
    Points: 26, Level: 1
    Level completed: 52%, Points required for next Level: 24

    Posts
    6
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Significance test for two proportions using SPSS

    Thanks for the reply Karabiner. I've done some more researching - could I also use a Chi-square test of independence between the two data sets? If not, is there a reason why not?

  4. #4
    TS Contributor
    Points: 17,742, Level: 84
    Level completed: 79%, Points required for next Level: 108
    Karabiner's Avatar
    Location
    FC Schalke 04, Germany
    Posts
    2,539
    Thanks
    56
    Thanked 639 Times in 601 Posts

    Re: Significance test for two proportions using SPSS

    What do you mean by data sets, exactely?
    You said "I have a binary data set". Therefore, I
    assumed that there are several binary variables,
    measured within the same sample. This would be
    a repeated measures (dependent samples) design,
    and Chi² is for independent groups. But maybe
    your data set looks different. Perhaps you should
    desribe your research in a bit more detail first (topic,
    research question, design, variables, sample size).

    With kind regards

    K.

  5. #5
    Points: 26, Level: 1
    Level completed: 52%, Points required for next Level: 24

    Posts
    6
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Significance test for two proportions using SPSS

    Sure - sorry I realise I was quite confusing.

    Basically I have one data set with binary responses to three conditions (Baseline, A and B).
    My design is within subjects (repeated measures), so they all respond to baseline, condition A and condition B. I wish to compare the proportions of response to baseline to those proportions of condition A and then condition B. My sample size is 32 (32 responses in baseline, condition a and b).

    Hopefully that makes more sense.
    Thank you!

  6. #6
    TS Contributor
    Points: 17,742, Level: 84
    Level completed: 79%, Points required for next Level: 108
    Karabiner's Avatar
    Location
    FC Schalke 04, Germany
    Posts
    2,539
    Thanks
    56
    Thanked 639 Times in 601 Posts

    Re: Significance test for two proportions using SPSS


    Repeated measures of binary responses can be analysed using Cochran's Q and McNemar's test.
    Chi² tesf for independence, in contrast, is for independent samples.

    With kind regards

    K.

+ 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