Title: Stochastic spanning and investment opportunities
Authors: Sofia Anyfantaki - Athens University of Economics and Business and Bank of Greece (Greece) [presenting]
Nikolas Topaloglou - Athens University of Economics and Business Research Center (Greece)
Stelios Arvanitis - RC-AUEB (Greece)
Abstract: The notion of stochastic spanning is generalized to avoid uniformity over a class of investor preferences. This could be useful for developing tests for stochastic dominance efficiency with better properties. We derive an analytical characterization for stochastic spanning and the null limit distribution for the associated empirical test statistic. We also develop a subsampling procedure for the approximation of the asymptotic critical values and show asymptotic exactness when the significance level is restricted to a continuity point of the limiting quantile function and the null limit distribution is not degenerate. Consistency is also derived. An approximation that is numerically implementable is also provided. We employ the stochastic spanning approach to the question of whether to include cryptocurrencies in investors' portfolios. We further explain our results by documenting that cryptocurrency markets are segmented from the equity and bond markets.