Ancova for nested design experiment, three factors

Home Forums Default Forum Ancova for nested design experiment, three factors

Viewing 1 post (of 1 total)
  • Author
    Posts
  • #2486
    Benjamin Quaiser
    Participant
    Hi all,

    I definitly need your help for evaluating my experiment:

    I ran a field experiment in which I designed 5 different groups:
    1 Control group (label Treat, coded 0 for control, 1 for any kind of treatment)
    2 Factorlevel A (coded 1 for S, 2 for R, and 0 for control)
    2 Factorlevel B (coded 1 for L, 2 for H and 0 for control)

    I measured post-level of a DV and treat pre-level of this DV as a covariate (v_555_0).

    Because this is not a fully crossed design, a nested design approach must be appropriate.
    First of all, do you think this is a nested design?
    And if so, how could I handle this in SPSS?
    I ran:
    ATASET ACTIVATE DatenSet1.
    UNIANOVA v_555__1 BY Treat GruppeSR GruppeLH WITH v_555__0
    /METHOD=SSTYPE(3)
    /INTERCEPT=INCLUDE
    /EMMEANS=TABLES(Treat) WITH(v_555__0=MEAN) COMPARE ADJ(BONFERRONI)
    /EMMEANS=TABLES(GruppeSR) WITH(v_555__0=MEAN) COMPARE ADJ(BONFERRONI)
    /EMMEANS=TABLES(GruppeLH) WITH(v_555__0=MEAN) COMPARE ADJ(BONFERRONI)
    /PRINT=HOMOGENEITY
    /CRITERIA=ALPHA(.05)
    /DESIGN=v_555__0 Treat GruppeSR(Treat) GruppeLH(Treat).

    I cannot run planned contrast, but Bonferroni works.
    Do you think this is the right procedure? Or do I have to evaluate my design totally different?

    Thanks a lot for your help and effort!
    Benjamin


Viewing 1 post (of 1 total)
  • The forum ‘Default Forum’ is closed to new topics and replies.