In previous posts, we learned how to use Python to detect group differences on a single dependent variable. However, there may be situations in which we are interested in several dependent variables. In these situations, the simple ANOVA model is inadequate.
One way to examine multiple dependent variables using Python would, of course, be to carry out multiple ANOVA. That is, one ANOVA for each of these dependent variables. However, the more tests we conduct on the same data, the more we inflate the family-wise error rate (the greater chance of making a Type I error).
This is where MANOVA comes in handy. MANOVA, or Multivariate Analysis of Variance, is an extension of Analysis of Variance (ANOVA). However, when using MANOVA we have two, or more, dependent variables.
MANOVA and ANOVA is similar when it comes to some of the assumptions. That is, the data have to be:
- normally distributed dependent variables
- equal covariance matrices)
In this post will learn how carry out MANOVA using Python (i.e., we will use Pandas and Statsmodels). Here, we are going to use the Iris dataset which can be downloaded here.