Dear all,
I conducted a beetween-subjects experiment with two different groups which where exposed randomly to two different type of messages (activational or non-activational). The outcome variable was meassured before and after the experimental scenario. Now I need to test additionally, if several moderators (measured once) affected the outcome variable.
How do I proceed here? My hypothesis is formulated as follows:
At same type of message (so activational or no-activational), moderator XY leads to higher values in the outcome variable.
I am very happy for your help on this.
Thank you very much in advance.
3 way Anova of the differences in outcome variable before/after moderator message.
the three dimensions being subject (say 20 in each group) moderator ( say 1-4) and message type (activ or nonactiv) . this would be a 20x 4 x 2 Anova
If there were two groups that were each exposed to two different treatments, then this really constitutes one group. You need randomly selected discrete groups, then expose the different groups to one type of message only and also replicate this. Then you can compare them using t tests or anova if the data is normally distributed (and independent) or using the Mann-Whitney test or permanova if the data is nonparametric and also independent
- Badges
- Science method
- Similar topics
- Mathematics
- Statistics
- Statistical Techniques
- Structural Equation Modeling