An unbiased variance estimator for overlapping returns
Redirect to publisher's version
(publisher's version.url.txt, 43 bytes)
This paper gives an unbiased estimator of the variance of overlapping returns. The estimator improves upon that proposed in Lo and MacKinlay (1988) [LM] (which is widely used in practice), as the LM estimator is consistent but not unbiased in small samples. The relevance of unbiasedness for variance ratio tests in a simulation experiment is illustrated.