- CFA Exams
- CFA Level I Exam
- Topic 1. Quantitative Methods
- Learning Module 2. Multiple Regression
- Subject 6. Assumptions of the Multiple Linear Regression Model
CFA Practice Question
Which of the following is not an assumption used in constructing and interpreting multiple linear regression models?
A. The expected value of the error terms must be equal to zero, and the variance of the error terms must remain stationary.
B. The error terms must have a uniform distribution.
C. A perfect linear relation must not exist between two or more of the independent variables.
Explanation: A uniform distribution implies that each value of the error term has an equal probability of occurring. This contradicts the assumption of linear regression in that the errors must exhibit a normal distribution, with the mean equaling to zero.
User Contributed Comments 1
| User | Comment |
|---|---|
| dblueroom | About C: The assumption doesn't specifically say only perfect linear relationship constitute a violation. there usually is some degree of correlation between independent variables, but not significant enough to be considered as a violation. |