financial assets performance evaluation using data envelopment analysis under skewed t distribution

The purpose of this study is to introduce a dea model to evaluate financial assets performance. in real-world data, returns distribution exhibit skewness and kurtosis which these parameters influence on the asset performance. therefore, in order to properly measure the performance, multivariate distributions should be adopted. for this purpose, skewed t distribution is applied, due to its efficiently fitted property to data. thus, we introduce a dea-based model which we have considered value at risk and conditional value-at-risk, two risk measures as inputs and mean return along with traditional performance indexes as inputs and the skewed t as the underlying distribution. the em algorithm is applied to estimate the skewed t distribution parameters. finally, we present an empirical application of iran stock market to demonstrate the usefulness of the proposed model, and we compare the results by using the normal as the underlying distribution.