Multiplying an estimating equation by a correcting factor to correct heteroskedasticity may cause extra correlation to enter the model, which raises the R^2. This renders our ultimate regression results meaningless. True or false, or uncertain? Please provide an explanation.© BrainMass Inc. brainmass.com October 24, 2018, 9:03 pm ad1c9bdddf
The answer is false. A regression model is useless until all the regression assumptions are satisfied. So a regression model where Heteroskedasticity is not satisfied is a useless model. We must make necessary correcting adjustments to remove Heteroskedasticity.
Multiplying a regression ...
Explains why a regression model where Heteroskedasticity is not satisfied is a useless model.
Heteroskedasticity Residual Plots
I am attaching three different residual plots. I am trying to determine whether heteroskedasticity is present. I don't believe I see any pattern indicative of heteroskedasticity (nonconstant variance). I know it can be difficult to detect - do you see any indication of this?View Full Posting Details