1: Multiple Regression

Question 1

Non constant variance of the error term is unrelated to Independent Variables

Answer 1

Unconditional Heteroskedacity

ignore (doesn’t cause issues)

Question 2

Evaluating regression models:
AIC measures

Answer 2

Lower AIC = Better forecast

Question 3

Evaluating regression models: BIC

Answer 3

Lower BIC= Better Fit

Question 4

Assumptions of Linear Regression

Answer 4

• Linear relationship between X & Y
• No exact linear relationship between any X
• X is not random
• Residuals are normally distributed
• Variance of residuals is constant (homoskedacity)
• The error term is uncorrelated across observations
• Expected value of the error term =0

Question 5

Cook’s Distance detects:

Answer 5

influential data points

Question 6

F-test is used for evaluating overall:

Answer 6

model fit

not adjusted R2