I have a question about whether statistical analysis to conduct in SPSS.
I have a factor that includes two levels. Also, I have multiple dependent variables with repeated measures.
Which statistical analysis is more suitable? A one-way repeated measures ANOVA with the independent factor (between-subjects) and time (within-subjects) or something else?
Based on your description:
1- I have a factor
2- multiple dependent variables with repeated measures
Therefore
Your model is one-way repeated measures MANOVA.
Which can be done easily using SPSS.
You say you have multiple dependent variables (with repeated measures). But what of your research question or questions? Do you have one multivariate question or multiple univariate questions? The answer to that question should dictate the approach you take. See the classic article by Huberty & Morris (1989) for more discussion of this issue. HTH.
Article Multivariate Analysis Versus Multiple Univariate Analyses
For a repeated measures ANOVA with more than 2 levels on the within (repeated measures) factor, you should check the Sphericity (homogeneity of covariances). If significant (lack of homogeneity), you might want to run a MANOVA or correct for this lack.
see:
https://statistics.laerd.com/statistical-guides/sphericity-statistical-guide.php
Thank you all for your valuable Information. There is no sphericity violation.
As I have mentioned before, there is one independent variable with two levels and five dependent variables that have been measured repeatedly (3 times). I want to write a report and interpret the results. I am confused about which analysis is the best.
As Bruce wrote, it depends on what you are interested in, the article he provided gives good overview when it is reasonable to use a MANOVA approach and when several ANOVAs.
If you are interested in the multivariate approach, technically you have a "doubly multivariate ANOVA", doubly because you have two sources of repeated measures, the reptetition in time (3 times) and 5 dependent variables (so you have technically 15 variables). You can find a good explanation and code for different statistical programs for such designs in Tabachnick & Fidell - Using Multivariate Statistics.
Olusegun Emmanuel Ogundele how do you come to this conclusion? As Bruce Weaver already pointed out, the decision depends on what the goal of the study is. How can you be sure what he "has to" use?
- Badges
- Science method
- Similar topics
- Mathematics
- Statistics
- Statistical Modeling
- Analyses of Variance
- ANOVA