+ Reply to Thread
Results 1 to 2 of 2

Thread: ANCOVA/MANCOVA vs. Mixed models

  1. #1
    Points: 372, Level: 7
    Level completed: 44%, Points required for next Level: 28

    Posts
    5
    Thanks
    1
    Thanked 0 Times in 0 Posts

    ANCOVA/MANCOVA vs. Mixed models




    Iíve been asked to consult on a study that is essentially a case-control study. The researchers matched cases and controls on 3 variables. The outcomes are test scores and subscale scores. The subjects didnít receive the same tests multiple times, but each person contributed several test scores at the end of the study period. Every subject provided data for every test (i.e., no missing data).

    The researchers used ANCOVA/MANCOVA which doesnít account for the matching. I suggested using a 3-level mixed model with outcomes nested within subjects and subjects nested within matched pairs. The researcher would prefer to stick with the ANCOVA/MANCOVA approach but to enter the matching variables as random effects.

    Is that valid, or should I insist on mixed models?

    Thanks!

  2. #2
    Pirate
    Points: 15,159, Level: 79
    Level completed: 62%, Points required for next Level: 191
    victorxstc's Avatar
    Posts
    875
    Thanks
    229
    Thanked 332 Times in 297 Posts

    Re: ANCOVA/MANCOVA vs. Mixed models


    ANCOVA with random effects for the matched variables is actually a mixed model. So their approach is valid too.
    "victor is the reviewer from hell" -Jake
    "victor is a machine! a publication machine!" -Vinux

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

    thirty006 (10-10-2013)

+ 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