PORTFOLIO OPTIMIZATION OF DYNAMIC COPULA MODELS FOR DEPENDENT FINANCIAL DATA USING CHANGE POINT APPROACH
COMMUNICATIONS FACULTY OF SCIENCES UNIVERSITY OF ANKARA-SERIES A1 MATHEMATICS AND STATISTICS, cilt.65, sa.2, ss.175-188, 2016 (ESCI, TRDizin)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 65 Sayı: 2
- Basım Tarihi: 2016
- Doi Numarası: 10.1501/commual_0000000768
- Dergi Adı: COMMUNICATIONS FACULTY OF SCIENCES UNIVERSITY OF ANKARA-SERIES A1 MATHEMATICS AND STATISTICS
- Derginin Tarandığı İndeksler: Emerging Sources Citation Index (ESCI), TR DİZİN (ULAKBİM)
- Sayfa Sayıları: ss.175-188
- Anahtar Kelimeler: Dynamic copula, change point, Conditional Value at Risk (CVaR), portfolio optimization
- Ankara Üniversitesi Adresli: Evet
Özet
In this paper, the portfolio optimization based on CVaR is performed using the dynamic copula model for financial data. Determining the best model of dependency between financial data has an important role in taking appropriate investment decisions. Due to the financial data is always affected by the fluctuations of the economic factors, the dynamic model was handled. On the other hand change point detection is also important for investment decisions. So this study presents an application of dynamic copula model with change point approach. We take the currency data (USD and EUR) from Turkish Central Bank to construct a portfolio. This study consists of two stages. In the first stage, the marginal distributions and copula models of currency data are defined for full sample, and the portfolio optimization based on CVaR is performed. In the second stage, the change periods of copula models are determined using binary segmentation method, and the portfolio optimization based on CVaR is performed for each period.