Least Squares Estimation Using Sketched Data with Heteroskedastic Errors. (arXiv:2007.07781v2 [stat.ML] UPDATED)

Researchers may use a sketch of data of size $m$ instead of the full sample
of size $n$ sometimes to relieve computation burden, and other times to
maintain data privacy. This paper considers the case when full sample
estimation would have required the Eicker-Huber-White robust standard errors to
account for heteroskedasticity. We show that random projections have a
smoothing effect on the sketched data, with the consequence that the least
squares estimates using such sketched data behave 'as if' the …

arxiv data errors least ml squares