+ Reply to Thread
Results 1 to 2 of 2

Thread: What method is recommended, use contrast or t.test

  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

    Post What method is recommended, use contrast or t.test




    I have a set with 60 observations, in four groups t1,t2,m1,m2 each with 15 observations. If I want to compare t1,t2 to m1,m2 or t1,m1 to t2,m2 what I did was to create a new variable so I can group the observations in 2 groups t and m and on the second iteration groups 1 and 2 then I just used a t.test basically to compare the group means... I was told that what I should've done is use CONTRASTS instead because the t.test doesn't take variance into account.

    Why is this? can someone please expand on this or if it is better to use t.test as I did?

  2. #2
    TS Contributor
    Points: 12,227, Level: 72
    Level completed: 45%, Points required for next Level: 223
    rogojel's Avatar
    Location
    I work in Europe, live in Hungary
    Posts
    1,470
    Thanks
    160
    Thanked 332 Times in 312 Posts

    Re: What method is recommended, use contrast or t.test


    Hi,
    this might be a bit of a misundetstanding: the vanilla t.test assumes equal variances, but so does anova. Moreover, you can run a t.test without the equal variance assumption. You might want to adjust for false positives though -e.g. by applying the Bonferroni correction for your t-tests.

+ 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