Weighted Least Squares and Residuals
Attached is a sample of real estate sales and house sizes. If you build a model predicting price as a function of size, there is clear evidence of nonconstant variance. So, I created a weight column to do a weighted least squares regression. However, the residual pattern never changes - I tried weights = 1/size, then size squared, cubed, etc. The residual pattern appears exactly the same until...
