Figure 1 shows a sample data including the two classes. Both logistic regression and Naive Bayes methods can be applied to classify the data without any error. One reason is that there is a gap area known as a decision boundary that logistic regression and Naive Bayes can search for to separate the two classes. Figure 2 illustrates a decision boundary that can be used for classification.

Figure 1

enter image description here

Figure 2

enter image description here Finding a decision boundary can difficult in some other dataset. If logistic regression or Naive Bayes cannot find a correct decision boundary, their classification results would involve a serious error. Can you provide an example of 2-dimentaional data in the format of Figure 2 for each of the following situations?

1) Logistic regression can find a decision boundary correctly, whereas Naive Bayes cannot.

2) Naive Bayes can find a decision boundary correctly, whereas logistic regression cannot.

  • $\begingroup$ You are assuming the boundary is real. See this. $\endgroup$ – Frank Harrell May 20 '18 at 11:47

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.