Application of ARMA-GARCH Returns Generation in Portfolio Selection Process

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27510%2F22%3A10250227" target="_blank" >RIV/61989100:27510/22:10250227 - isvavai.cz</a>

Výsledek na webu

<a href="https://mme2022.vspj.cz/download/proceedings-2.pdf" target="_blank" >https://mme2022.vspj.cz/download/proceedings-2.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Application of ARMA-GARCH Returns Generation in Portfolio Selection Process

Popis výsledku v původním jazyce

In this paper, we examine the application of a return scenario generation procedure in the portfolio optimization strategy based on an ARMA-GARCH model. We assume that residuals follow a stable distribution and the dependency structure of residuals is determined by Student t and skewed t copula. Moreover, we analyse the modification in dependency estimation of residuals obtained from the ARMA-GARCH model in order to find an appropriate setting. Then, we compare the effect of selected return approximation methods on the ex-post portfolio wealth and statistics determined using a portfolio model maximizing selected widely used reward-risk measures. Additionally, the strategy consists of monthly re-optimization and transaction costs expressed proportionally. The following empirical analysis on the U.S. market data allows us to evaluate the impact of return approximation in the portfolio optimization process. Results obtained using analysed approaches generate lower risk with affecting portfolio performance for certain models compared to the benchmark.

Název v anglickém jazyce

Application of ARMA-GARCH Returns Generation in Portfolio Selection Process

Popis výsledku anglicky

In this paper, we examine the application of a return scenario generation procedure in the portfolio optimization strategy based on an ARMA-GARCH model. We assume that residuals follow a stable distribution and the dependency structure of residuals is determined by Student t and skewed t copula. Moreover, we analyse the modification in dependency estimation of residuals obtained from the ARMA-GARCH model in order to find an appropriate setting. Then, we compare the effect of selected return approximation methods on the ex-post portfolio wealth and statistics determined using a portfolio model maximizing selected widely used reward-risk measures. Additionally, the strategy consists of monthly re-optimization and transaction costs expressed proportionally. The following empirical analysis on the U.S. market data allows us to evaluate the impact of return approximation in the portfolio optimization process. Results obtained using analysed approaches generate lower risk with affecting portfolio performance for certain models compared to the benchmark.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

50206 - Finance

Projekt

<a href="/cs/project/GA20-16764S" target="_blank" >GA20-16764S: Zobecněný přístup ke stochastické dominanci: teorie a finanční aplikace</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

40th International Conference Mathematical Methods in Economics 2022 : Proceedings : College of Polytechnics Jihlava : 7 – 9 September 2022, Jihlava, Czech Republic

ISBN

978-80-88064-62-6

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

250-256

Název nakladatele

College of Polytechnics Jihlava

Místo vydání

Jihlava

Místo konání akce

Jihlava

Datum konání akce

7. 10. 2022

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

000936355000039