Chapter 5 (5.3.2-5.4.2) - Controlling for Confounders Using Multiple Linear Regression

Question 1

When dealing with observational data, what should the first step be?

Answer 1

To identify potential confounders in the relationship between X and Y.

Question 2

True or false: multiple linear regression models have one just X variable.

Answer 2

False

Question 3

What are “post-treatment” variables?

Answer 3

Variables that are affected by a treatment.

Question 4

True or false: you can’t rely on random treatment assignment to eliminate potential confounders.

Answer 4

True

Question 5

What are confounders?

Answer 5

Variables that affect 1. the likelihood of receiving the treatment and 2. the outcome.

Question 6

Adding all confounders as controls in the model makes what?

Answer 6

It makes the treatment group and the control group comparable after controls.