Hi everyone, I would appreciate to tell me you suggestion:
I’m going to compare just two independent group. The outcome variables are continuous -one of them has 5 subclass and another one has 4 subclass-
I am thinking to apply running separate t-test for each subclass of these outcome variables (to compare total score and subclass score).
Then will consider adjusting for multiple comparisons to control the Type I error rate by Bonferroni correction.
But as I have one confounding variable, so will ignore T-test and apply ANCOVA?
Am I correct, ANCOVA is the best for my goal?
- "To compare total score and subclass score". You're suggesting comparing the total score to the component scores that make up that total score ?
It's fine to consider all those as separate dependent variables and analyze them separately.
If so, you'll have 10 different t-tests. As you mention, it may be a good idea to consider p-value adjustment for multiple hypothesis tests. You may or may not consider this adjustment necessary, depending on your goals.
If you wish to include your other independent (confounding) variable, then yes, ancova is probably appropriate. If you take this approach, there is no need to do the t-tests.
Thanks for clarifying. With n=135 per group, and with 9 DVs, you might consider using the approach Frank Harrell described in the attached excerpt from his regression modeling book. I.e., estimate a binary logistic regression with Group as the DV and with the 9 subclass scores as explanatory variables. HTH.
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Regression