Hi everybody,
I have two experimental groups (vehicle- vs drug-treated) and two time points. I plotted correlated activity of different brain regions in each group, at each time point. Now, I would like to determine whether the correlated brain activity statistically differs between the two groups and two time points (so 2x2 design, but no matching or pairing across time). So far, I could not find a method to compare the strength of the correlations between two (or more) groups. Does anyone have experience in this?
Many thanks!
Best, Kübra
Dear Kübra, so you collected data from each mice twice? In that case, two way repeated measures ANOVA is the proper statistical probe. Drug effect, time effect and their interaction should be analyzed.
If you have two groups (vehicle, drug) for the first time point, and the same grouping schedule, but different mice for the second time point, you could analyze the data of the two time points separately, by independent samples t-test.
So, if the mice were sacrified after the first measurement and the second measurement were conducted on different mice, it's independent samples t-test. If you used the same mice for both measurements (both time points), it's two way repeated measures ANOVA.
To compare the strength of the correlations between two groups and two time points, you can use Fisher's z-transformation. Once you have obtained the Fisher's z-transformed correlation coefficients for each group and time point, you can use them as the dependent variable in a two-way ANOVA. This will allow you to determine whether there are significant differences in the strength of the correlations between the two groups and two time points.
I suggest you to do the ANOVA on the transformed correlation coefficients, because they are approximately normally distributed, making them easier to analyze statistically.
Hi Kübra,
You can use ANCOVA to check the effect of a nominal variable on the correlation between two continuous variables. I think you want to find the correlation between two regional activities, and you have two independent nominal variables of group and time points. So, you can use two-way ANCOVA to explore the effect of time and group on the regional coactivations.
- Badges
- Science topic
- Similar topics
- Methodology
- Research Methodology
- Research Papers