Statistical Inference for the Expected Utility Portfolio in High Dimensions

In this paper, using the shrinkage-based approach for portfolio weights and modern results from random matrix theory we construct an effective procedure testing efficiency of expected utility (EU) discuss asymptotic behavior proposed test statistic under high-dimensional regime, namely when number assets $p$ increases at same rate as sample size $n$ such that their ratio $p/n$ approaches a positive constant $c\in(0,1)$ $n\to\infty$. We provide extensive simulation study where power function receiver operating characteristic curves are analyzed. empirical study, methodology is applied to returns S\&P 500 constituents.