Quant Memo
Statistics/●●●●

Heteroskedasticity breaks your standard errors, not your coefficients

Asked at Squarepoint

Your regression errors have non-constant variance, volatility clusters, so Var(εiX)\operatorname{Var}(\varepsilon_i \mid X) changes across observations.

Does this bias your OLS coefficients? If not, what exactly does it break, and how do you fix it?

Show a hint

Which part of the classical OLS results uses the constant-variance assumption, the point estimates, or their standard errors?

Your answer

This one is open-ended. Work it through, then check your reasoning against the full solution.

More Statistics questions