作者: Bruce N. Lehmann , David M. Modest
关键词:
摘要: Nontrivial diversification possibilities arise when a factor model describes security returns. This paper catalogs the merits of alternative strategies for constructing basis portfolios to mimic common factors. We show how use ? 2 statistic joint significance mean portfolio returns rank procedures and bootstrap perform inferences on disparity between statistics across formation procedure, estimation method, cross-section size, number Our main conclusion is that maximum likelihood analysis coupled with minimum idiosyncratic risk yields economically statistically superior compared those derived from asymptotic principal components.