If you are on ResearchGate and care to comment, or if you aren't and just want to check it out, the following is on the fundamental nature and magnitude of heteroscedasticity, for regressions of form y = y* + e, most useful in predictions for finite populations:
https://www.researchgate.net/project/OLS-Regression-Should-Not-Be-a-Default-for-WLS-Regression Please see the project updates, and also particularly note
https://www.researchgate.net/publication/320853387_Essential_Heteroscedasticity, which explores a succinct and important analysis by Ken (KRW) Brewer on this topic.
Ken's insight on this matter is very keen and has not received the attention it merits. For that reason, and linking one of the papers Ken did on statistical history, I recently posted a version of this post to the History of Statistics Interest Group.
Hooroo -
------------------------------
James Knaub (Jim)
Retired Lead Mathematical Statistician
------------------------------