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.

Stepwise logistic regression

Stepwise logistic regression

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

Start my 1-month free trial

Stepwise logistic regression

“

- [Instructor] Okay, we're gonna try the stepwise method on logistic regression. Only discriminant analysis and logistic will have stepwise. Now, that doesn't mean that they're the only algorithms that choose variables for you, but they're the only ones that use the stepwise approach. So I'm gonna start with a larger pool of variables, age, passenger class, embarked, sex, sibling spouse, parent child, and fare. Let's see what the logistic had to say about these variables. It starts by picking the one that has the best statistical significance. Then it grabs another. Then it grabs another. Then it grabs another. And at a certain point, there's no additional variables that are statistically significant at whatever threshold is set, usually .05. Embarked was not picked up, parent child was not picked up, and fare was not picked up. But all the others were.

Contents