Covariance Implied Risk Factors

Covariance Implied Risk Factors

• Autor
• mohammed mehdi kaebi
• Resumo

• This paper examines the role of heteroskedasticity in extracting latent risk factors from asset returns. I show that standard principal component analysis suffers from distortions when assets exhibit heterogeneous idiosyncratic variances, leading factors to reflect clusters of idiosyncratic risk rather than true systematic risk. Building on recent developments in the statistics literature, I apply heteroskedastic PCA (heteroPCA) to correct for this bias by iteratively replacing the diagonal of the sample covariance matrix with estimates implied by the off-diagonal structure. This approach delivers superior out-of-sample cross-sectional pricing performance compared to standard PCA, with higher Sharpe ratios and lower average pricing errors across multiple equity portfolios. The identified factors exhibit clear economic interpretability, and the implied stochastic discount factor achieves lower Hansen-Jagannathan distances. These results highlight that accounting for heteroskedasticity in idiosyncratic variance substantially improves factor estimation in asset pricing applications.

• Palavras-chave
• Factor models, principal component analysis, heteroskedasticity, asset pricing, latent factors.
• Modalidade
• Comunicação oral
• Área Temática
• Apreçamento de Ativos

Voltar Download