+ Reply to Thread
Results 1 to 2 of 2

Thread: ANOVA or T-test

  1. #1
    Points: 2,096, Level: 27
    Level completed: 64%, Points required for next Level: 54

    Posts
    12
    Thanks
    5
    Thanked 0 Times in 0 Posts

    ANOVA or T-test




    Hi
    I have two categorical variables as in below example:
    Code: 
    Region	Dim	Value
    PK	Dim1	2
    PK	Dim2	3
    PK	Dim3	-1
    PK	Dim4	-4
    US	Dim1	-0.5
    US	Dim2	4.3
    US	Dim3	2.1
    US	Dim4	2
    PK	Dim1	5
    PK	Dim2	-0.4
    PK	Dim3	-0.3
    PK	Dim4	0.8
    US	Dim1	1
    US	Dim2	2
    US	Dim3	0.8
    US	Dim4	1
    I want to compare the variables US and PK, if they are different from each other with respect to any or all of the four attributes (Dim1, Dim2, Dim3, Dim4). My question is:
    1. Should I use a one way ANOVA and then post hoc (for example HSD Tukey) to determine if these two variables have any significant differences at any of these 4 attributes (PKDim1-USDim1, PKDim2-USDim2...)?
    Since I have to report the results in 1 graph (box plot), i thought using an ANOVA would be fine. But, the issue of non-desirable group comparisons (e.g. PKDim1-PKDim2....) is confusing. Is it acceptable to perform ANOVA in such situations?
    OR
    2. Should i just preform T-test 4 times, for example US versus PK on Dim1, Dim2, Dim3 and Dim4. And report each one separately.
    Your helpful comments will be highly valuable.

  2. #2
    TS Contributor
    Points: 14,811, Level: 78
    Level completed: 91%, Points required for next Level: 39
    Miner's Avatar
    Location
    Greater Milwaukee area
    Posts
    1,171
    Thanks
    34
    Thanked 405 Times in 363 Posts

    Re: ANOVA or T-test


    Since you only have two levels of region, either test will yield identical results with no need of a post-hoc test for the 1-way ANOVA. You would run either test once for each dependent variable (i.e., Dim1, Dim2,...), so you would not the non-desirable group comparisons.

  3. The Following User Says Thank You to Miner For This Useful Post:

    true_friend (03-13-2017)

+ 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