There is a task that doesn't appear to make much sense to me in a textbook. I have a dataset of categorical variables (the features and target are categorical) . I am asked to determine what are the most important variables that explain the target variable and whether they are statistically significant. I have always thought that variable ranking can only be achieved by applying a supervised learning algorithm such as logistic regression or random forests, boosting etc but that is explicitly not allowed in this task. How can I otherwise do this?

  • $\begingroup$ PCA? maybe you can check the singolar valuees and those are supposed to be the must relevant feature $\endgroup$ Jul 2 at 16:16


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.