CANTÜRK KAYAHAN, OĞUZHAN AYDEMİR, Barış AKÇAY

Döviz piyasalarında EWMA modeli kullanılarak hesaplanan volatilite tahminlerinin test edilmesi

Finansal piyasalarda yaşanan ekonomik, politik, sosyal ve global gelişmeler döviz kurlarını ve diğer finansal enstrümanları doğrudan etkilemekte ve onların getiri değişimlerinde önemli derecede oynaklıklara neden olmaktadır. Volatilite tahminleri varlık yönetiminde, portföy yönetiminde ve türev ürün fiyatlamasında yoğun olarak kullanılmakta ve finansal piyasalar için anahtar rol üstlenmektedir. Günümüzde hiçbir finansal analist bu modellerin önemini görmezden gelemez. Volatilite modellerinin temel amacı, volatilitenin doğru tahmin edilmesidir. Çünkü geleceğe yönelik alınan kararların başarısı bu tahminlerin tutarlılığına bağlıdır. Çalışmada, yıllar itibariyle döviz kurlarının EWMA modeliyle volatilite tahminleri yapılmıştır. Hesaplamalarda 2005, 2006 ve 2007 yıllarına ait döviz kurları (euro ve dolar) kullanılmış ve volatilite tahmin sonuçları EWMA modelinde günlük ve yıllık olarak sunulmuştur. Yapılan backtesting analiziyle, hesaplamalarda kullanılan lambda katsayılarının EWMA modelinde belirlenen güven sınırları içerisinde anlamlı tahminler oluşturduğu saptanmış ve böylece modelin güvenirliği de test edilmiştir.

Economic, politic, social and global developments in financial markets affect exchange rates and other financial instruments directly and cause volatility in their yield changes significantly. Volatility estimations are used in asset management, portfolio management and derivative product pricing intensely and play critical role for financial markets. Nowadays, financial analysts can't ignore the importance of these models. The aim of volatility models is the correct estimation of volatility since the success of future decisions depends on the consistency of these estimations. In this study, volatility estimations of exchange rates by the means of EWMA model are performed by years. In the calculations, foreign exchange rates (euro and dollar) of 2005, 2006, and 2006 years are used and the results of volatility estimation are presented as daily and yearly in EWMA model. The result of backtesting analysis states' that lambda coefficients used in calculations compose significant estimations within confidence limits determined in EWMA model and thus the reliability of model is tested.

PDF

___

BIS (Bank For International Settlement), Triennial Central Bank Survey, Foreign Exchange and Derivatives Market Activity, December 2007, Basel, Switzerland.

Bolgün, Evren ve Akçay, Barış (2005), Risk Yönetimi, Scala Yayıncılık, İstanbul.

Bollerslev, Tim (1986), "Generalized Autoregressive Conditional Heteroskedasticity", Journal of Econometrics 31, North Holland, pp.307-327.

Brooks Chris and Persand Gita (2003), "Volatility Forecasting for Risk Management", Journal Of Forecasting, Published online 9 October 2002 in Wiley InterScience (www.interscience.wiley.com).DOI: 10.1002/for.841

Butler, Cormac (1999), Matering Value at Risk, Financial Times Prentice Hall, Great Britian.

Cheong, Chongcheul (2004), Does the risk of Exchange rate fluctuation really affect international trade flow between countries?, Economics Bulletin, Vol. 6, No: 4, pp. 1-8.

(http://www.economicsbulletin.eom/2004/volume6/A.pdf05.04.2008)

Gazda, Vladimir and VYROST, Tomas (2003), "Application of GARCH Models in Forecasting The Volatility of the Slovak Share Index (SAX)", Economic Focus, BIATEC, Volume XI, pp. 17-20.

Gıannapoulos, Kostas and Eales, Brian (1996), "Educated Estimates", Futures and Options World, April., http://currencies.thefmancials.com/FAQslb.html (22.02.2008).

Gıannopoulos, Kostas (2000), "Measuring Volatility", Ed.by.Marc Lore and Lev Borodovsky, Financial Risk Management, Garp, Butterworth -Heinemann, Oxford.

Hull, John C. (2000), Options, Futures, & Other Deriatives, Fourth Edition, Prentice Hall International Inc., U.S.A.

Jorıon, Philippe (2005), Financial Risk Manager-Handbook, Wiley Finance(Third edition), GARP(Global Ass. of Risk Professionals), Canada.

Kumar, S.S. (2006), Forecasting Volatility, Evidence from Indian Stock and Forex Markets, IIMK/WPS/08/FIN/2006/06. (www.dspace.iimk.ac.in/bitstream/ForecastingVolatility.pdf (15.04.2008).

Mcmilllan, David G. and SPEIGHT, Alan E.H. (2004), "Daily Volatility Forecast: Reassing the Performance of GARCH Models", Journal of Forecasting, pp. 449-460. Published online in Wiley InterScience (www.interscience.wiley.com). DOI: 10.1002/for.926

Mınkah, Richard (2007), U.U.D.M Project Report 2007/7, Forecasting Volatility, httpwww.math. uu.seresearchpubMinkah 1 .pdf (02.03.2007)

Ray, David (2003), Estimating Volatilities: Implied Volatility vs. Time Seties Volatility, www.unibas.ch/wwz/finance(12.02.2008).

Schmidt, Udo-Mohr (1995), Volatility Forecasting with Nonlinear and Linear Time Series Model: A Comparison, Frankfurt, Germany.

Sevil, Güven (2001), Finansal Risk Yönetimi Çerçevesinde Piyasa Volatilitesinin ve Portföy VAR Hesaplamaları, A.Ü. Yayınları, Eskişehir.

Suganuma, Ricardo (2000), Reality Check For Volatility Models, University of California, San Diego Department of Economics, httpwww.econ.puc-rio.brPDFsuganuma.pdf (12.02.2007)

TSE, Y. K. (1991), Stock Returns Volatility in the Tokyo Stock Exchange, Japan and the World Economy, 3, 285-298.

TSE, Y. K. and TUNG S. H. (1992), Forecasting Volatility in the Singapore Stock Market, Asia.Pacific Journal of Management 9,1-13.

http://www.numa.com/ref/volatili.htm(01.09.2006)

www.riskactive.com.tr (12.12.2007).

http://www.pricingtools.eu/sigmamodels/ewma.htm(12.04.2008).