About this question
Hard · Statistics & Regression · Quant Trader interview question · statistics, regression, heteroscedasticity, ols, standard-errors
You are building a statistical model to predict the daily returns of a volatile stock. After running an Ordinary Least Squares (OLS) regression, you suspect the presence of heteroscedasticity in the error terms. You know that heteroscedasticity doesn't bias the OLS coefficient estimates themselves, but it does affect the standard errors. You decide to use White's robust standard errors. Why are these robust standard errors still important even though the coefficient estimates are unbiased?