The diversification benefits of cryptocurrency asset categories and estimation risk: pre and post Covid-19

We examine the diversification benefits of cryptocurrency asset categories. To mitigate effects estimation risk, we employ Bayes-Stein model with no short-selling and variance-based constraints. estimate inputs using lasso regression elastic net regression, employing shrunk Wishart stochastic volatility Gaussian random projection. consider nine categories, find that all but two provide significant out-of-sample benefits. The lower is investor risk aversion, more beneficial are cryptocurrencies as portfolio diversifiers. During uncertain economic environments, such post-Covid-19 period, same in stable environments. Our results robust to different benchmarks, technique, transaction cost, constraints, higher moments Black–Litterman models.