From the course: Machine Learning & AI Foundations: Linear Regression
Unlock the full course today
Join today to access over 24,800 courses taught by industry experts.
Detecting curvilinearity - SPSS Tutorial
From the course: Machine Learning & AI Foundations: Linear Regression
Detecting curvilinearity
- [Instructor] When you're doing multiple linear regression obviously we're told that we have to have linear relationships, but we will often come across curvilinear relationships, and you have to know how to diagnose it and what you might be able to do as a corrective action when you do encounter it. So let's take a look. Let's go into Chart Builder. And we're gonna do a scatter plot with a trend line. And we're gonna go ahead and do beginning salary as our dependent variable. Education will be declared as a scale variable, otherwise Chart Builder won't behave properly. And I'm actually going to filter so that we're looking only at the males. Go ahead and run this. I've gotta put this in it's own window so we can easily see what we're up to. And there we go. So the question is, is this data possibly nonlinear? Well, we have some data points well above the regression line. Let's identify which data points those are. It's case ID 472, 473, number five, 359. You can see that. So the…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Contents
-
-
-
-
-
-
-
(Locked)
Collinearity diagnostics6m 30s
-
(Locked)
Dealing with multicollinearity: Factor analysis/PCA4m 17s
-
(Locked)
Dealing with multicollinearity: Manually combine IVs3m 15s
-
(Locked)
Diagnosing outliers and influential points7m 21s
-
(Locked)
Dealing with outliers: Studentized deleted residuals5m 49s
-
(Locked)
Dealing with outliers: Should cases be removed?6m 48s
-
(Locked)
Detecting curvilinearity5m 20s
-
(Locked)
-
-
-