I have some training and test data that I want to write my own QDA for (not use the existing function in R).

I'm struggling to understand the algorithm, for each of the k classes, are the mean vector and covariance matrices for each class estimated using the training data, and then plugging in each observation from the test data?

That's what I'm currently doing but am getting different prediction results when comparing with the function.


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.