We evaluate the performance of various methods for estimating factor returns in an approximate factormodel. Differences across estimators aremost pronounced when there is cross-sectional heteroscedasticity or when cross-sectional sample sizes, n, have fewer than 4,000 assets. Estimators incorporating either cross-sectional or time-series heteroscedasticity outperform the other estimators when those types of heteroscedasticity are present. The differences are most pronounced when the cross-sectional sample is small.
ASJC Scopus subject areas
- Economics and Econometrics