| Autor: |
ŠIKALO, Mirza, ARNAUT-BERILO, Almira, ZAIMOVIĆ, Azra |
| Předmět: |
|
| Zdroj: |
FEB Zagreb International Odyssey Conference on Economics & Business; Jun2021, Vol. 3 Issue 1, p752-768, 17p |
| Abstrakt: |
In this paper, we analyze the predictor efficiency of the model based on maximum loss return as a measure of risk and compare it with the model based on variance as a measure of risk to determine whether the maximum loss-based risk measure model is more suitable for use in certain circumstances than conventional return-risk models. For decades, the most famous return-risk model has been Markowitz's mean-variance model. On the other side, based on the tools provided by game theory, we present a minimax model for selecting the optimal portfolio based on maximum loss as a measure of risk. Recent research has shown the adequacy of the application of this risk measure and the dominance in relation to variance in certain circumstances. Theoretically, the model based on maximum loss as a measure of risk relies on a significantly smaller number of assumptions that must be met. We compare portfolios created on the basis of different models in the period from 2015 to 2020 from a selected sample of stocks that are constituents of the STOXX Europe 600 index, which covers 90% of the free market capitalization in the European capital market. The observed period includes the period of market decline during the COVID-19 crisis. As these models view risk in different ways, it is impossible to compare them solely through the risk dimension. Therefore, we compare the realized returns with the predictions offered by each model individually. The results show significantly higher stability of the portfolios selected on the criterion of minimizing the maximum loss. In periods of market decline, this portfolio achieves the best performance, and has a shorter recovery period than others. This allows superior use of the minimax model at least for investors with a pronounced risk aversion. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Supplemental Index |
| Externí odkaz: |
|
