Sample covariance matrices tend to underestimate the risk of optimized portfolios. In this article, we identify special portfolios, termed “eigenportfolios,” that capture these systematic biases. Further, we present a methodology for estimating eigenportfolio biases and for adjusting the...

We study whether analysts' recommendations and the market's reactions to recommendation changes are influenced by the structure of analysts' research portfolios. We find that analysts maintain more positive recommendations for stocks that belong to the “core industry” in their research...