New answers tagged

1 vote
Accepted

Understanding rare definition of the likelihood function and corresponding posterior from research paper

Imho, there is nothing rare there with the likelihood definition or notation except for a minor mistake. Here is the relevant excerpt from the paper: Hence there is a clear mistake/typo in using $\...
user avatar
  • 93.6k
1 vote
Accepted

interpreting confusion matrix results

To put it slightly differently, your model is able to catch 80.77% of the people who dropped out of workforce, and classified the rest otherwise able to catch only 18.52% of the people who are ...
user avatar
  • 52.6k
1 vote

If I engineer a new feature such that feature C = feature A/feature B, must I drop features A and B from a Gaussian Naive Bayes model?

You don't have to. It's true that Naive Bayesian assumes the features are independent conditioned on the class label. But it's OK to make wrong assumptions, because any model is just a set of ...
user avatar
1 vote

If I engineer a new feature such that feature C = feature A/feature B, must I drop features A and B from a Gaussian Naive Bayes model?

You are right, Naive Bayes requires that the features are conditionally independent. Conditionally here means, conditioned on the class (the dependent variable). And indeed, a new feature $C=A/B$ ...
user avatar
  • 6,633

Top 50 recent answers are included