From the course: Machine Learning and AI Foundations: Classification Modeling

Unlock the full course today

Join today to access over 22,600 courses taught by industry experts or purchase this course individually.

Discriminant with two categories

Discriminant with two categories

From the course: Machine Learning and AI Foundations: Classification Modeling

Start my 1-month free trial

Discriminant with two categories

“

- [Instructor] Okay, let's discuss a couple of technical issues to attend to while you're watching me demonstrate Discriminant Analysis on the Titanic data set. First, typcically, Discriminant Analysis will operate under listwise deletion, which means if anything's missing, the entire row is dropped. You don't know their age, you're gonna drop the case. You don't know their fare, that row is dropped. Some implementations will impute, meaning that they're gonna replace the missing data with some estimate. You don't know their age? You can replace with an average of age. There are also fancier versions of imputation. Next, all inputs are used typically in linear Discriminant Analysis. However, there is a technique, which we're gonna see, called Stepwise Discriminant Analysis, where it will choose the variables for you. Finally, and this is important and might even be surprising, remember that we're talking about linear Discriminant Analysis, this is for scale variables only. Your…

Contents