Question

In general, which of the following classification methods is the most resistant to gross outliers?
Quadratic Discriminant Analysis (QDA)
Linear Regression
Logistic regression
Linear Discriminant Analysis (LDA)

Answer 1

Answer:

6. In general, which of the following classification methods is the most resistant to gross outliers?

Quadratic Discriminant Analysis (QDA)

Linear Regression

Logistic regression

Linear Discriminant Analysis (LDA)

Answer :Logistic regression

Answer 2

The most resistant methods is Logistic regression.

• A group of findings with values diverging from predicted scope and efficiently generating exceptionally large residuals may imply an oddity referred to as outliers.
• The direct results of the study may be unduly affected by these outliers and lead to incorrect inferences.
• For logistic regression, the decision margin only considers the points more noticeable to it, so that the effect of outliers on the decision boundary is much less. Thus, an outlier can even so have a considerable impact on the boundaries.