Explore BrainMass

# Residual Plot in Regression: Homoskedasticity v. Heteroskedasticity

Not what you're looking for? Search our solutions OR ask your own Custom question.

This content was COPIED from BrainMass.com - View the original, and get the already-completed solution here!

Question 1
What pattern(s) would one like to see in a residual plot and why?
Question 2
a) State in algebraic notation and explain the assumption about the CLRM's disturbances that is referred to by the term homoscedasticity
b) What would the consequence be for a regression model if the errors were not homoscedastic?
c)How might you proceed if you found that (b) was actually the case?

https://brainmass.com/economics/regression/residual-plot-regression-homoskedasticity-heteroskedasticity-580311

#### Solution Preview

See the attached file.

Question 1
What pattern(s) would one like to see in a residual plot and why?
Answer: An ideal residuals plot would be showing a constant variance for the error term u, i.e. homoskedasticity (Var(u) = s2).
With the constant variance of the error term, each probability distribution for y (dependent variable) has the same standard deviation regardless of the x-value (independent variables).
This is important as one of the assumptions of the Classical Linear Regression Model (CLRM) that the error term has a constant variance (homoscedastic error). No heteroscedasticity.

Question 2
a) State in ...

#### Solution Summary

Implication of homoskedasticity, consequence of heteroskedasticity and remedy are discussed in the solution.

\$2.49