From the course: Machine Learning and AI Foundations: Classification Modeling
Unlock the full course today
Join today to access over 24,000 courses taught by industry experts.
Stepwise logistic regression
From the course: Machine Learning and AI Foundations: Classification Modeling
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
-
-
-
-
-
Overview2m 10s
-
(Locked)
Discriminant with three categories5m 44s
-
(Locked)
Discriminant with two categories5m 2s
-
(Locked)
Stepwise discriminant1m 3s
-
(Locked)
Logistic regression10m 54s
-
(Locked)
Stepwise logistic regression1m 3s
-
(Locked)
Decision Trees4m 46s
-
(Locked)
KNN3m 58s
-
(Locked)
Linear SVM8m 2s
-
Neural nets7m 57s
-
(Locked)
Bayesian networks7m 54s
-
(Locked)
Heterogenous ensembles3m 22s
-
(Locked)
Bagging and random forest3m 26s
-
(Locked)
Boosting and XGBoost1m 57s
-
-
-