Research Article
BibTex RIS Cite

CLASSICAL AND BAYESIAN APPROACH TO UNIVARIATE VOLATILITY MODELS

Year 2024, Volume: 9 Issue: 2, 91 - 111, 31.10.2024

Abstract

There are two different approaches to the development of statistics. These are the "Classical" and the "Bayesian" approaches. We encounter the concept of "objectivity", which in the classical approach refers to ignoring prior information about the process being measured. However, in the presence of prior information about the process under consideration, there is a loss of information because the existing information is ignored. Since the parameters are not random, probability statements about the parameters cannot be made. The Bayesian approach takes into account prior information about the process and takes a more disciplined approach to uncertainty. It is therefore an approach derived from Bayes' theorem. The Bayesian approach treats parameters as probabilistic and random variables. There are no assumptions to be made as in the classical approach. Given this information, the aim is to evaluate the univariate volatility models under the Classical and Bayesian approaches. Volatility, which corresponds to uncertainty in the financial markets, also represents the risk of the financial asset. Therefore, it is expected that it will be beneficial to evaluate the effect of both approaches on the analysis of volatility models.

References

  • Bauwens, L. L. (1999). Bayesyen inference in dynamic econometric models, New York: Oxford University Press.
  • Bauwens, L., Lubrano, M. (1998). Bayesian inference on GARCH models using the Gibbs Sample, Econometrics Journal, 1, 23-46.
  • Black, F. (1976). Studies of stock prices volatility changes, American Statistical Association, 177-181.
  • Bollerslev, T., Chou, R. Y., & Kroner, K. F. (1992). ARCH modelling in finance: A review of the theory and empirical evidence, Journal of Economerics, 52, 5-59.
  • Bollerslev, T. (1986). Generalized autoregressive conditional heteroskedasticity, Journal of Econometrics, 31(3), 307-327.
  • Bolstad, William M. (2004). Introduction to bayesian statistics, John Wiley&Sons.
  • Carter, C.K., R. Kohn. (1994). On gibbs sampling for state space models, Biometrika, 81, 541-553.
  • Chernozhukov, V., Hong, H. (2003). An MCMC approach to classical estimation. Journal of Econometrics, 115(2), 293-346.
  • Cowles, M.K., B.P.Carlin. (1996). Markov chain monte carlo convergence diagnostics: A comparative review, Journal of the American Statistical Association, 91, 883-905.
  • Çil, N. (2015). Finansal Ekonometri, Der Yayınları. Degiannakis, S., Xekalaki, E. (2004). Autoregressive conditional heteroscedasticity (ARCH) models: A review, Quality Technology & Quantitative Management, 1(2), 271-324.

TEK DEĞİŞKENLİ VOLATİLİTE MODELLERİNE KLASİK VE BAYESYEN YAKLAŞIM

Year 2024, Volume: 9 Issue: 2, 91 - 111, 31.10.2024

Abstract

İstatistiğin gelişiminde iki farklı yaklaşım vardır. Bunlar "Klasik" ve "Bayesci" yaklaşımlardır. Klasik yaklaşımda, ölçülen süreçle ilgili ön bilgilerin göz ardı edilmesini ifade eden "objektiflik" kavramı karşımıza çıkar. Ancak, söz konusu süreçle ilgili ön bilgilerin varlığında, mevcut bilgiler göz ardı edildiği için bir bilgi kaybı söz konusudur. Parametreler rastgele olmadığından, parametreler hakkında olasılık ifadeleri yapılamaz. Bayesci yaklaşım, süreçle ilgili ön bilgileri dikkate alır ve belirsizliğe daha disiplinli bir yaklaşım getirir. Bu nedenle Bayes teoreminden türetilmiş bir yaklaşımdır. Bayesci yaklaşım, parametreleri olasılıksal ve rastgele değişkenler olarak ele alır. Klasik yaklaşımda olduğu gibi sağlanması gereken varsayımlar yoktur. Bu bilgiler ışığında amaç, tek değişkenli volatilite modellerini Klasik ve Bayesyen yaklaşımlar altında değerlendirmektir. Finansal piyasalarda belirsizliğe karşılık gelen volatilite, aynı zamanda finansal varlığın riskini de temsil etmektedir. Dolayısıyla her iki yaklaşımın volatilite modellerinin analizine etkisi açısından değerlendirilmesinin faydalı olacağı beklenmektedir.

References

  • Bauwens, L. L. (1999). Bayesyen inference in dynamic econometric models, New York: Oxford University Press.
  • Bauwens, L., Lubrano, M. (1998). Bayesian inference on GARCH models using the Gibbs Sample, Econometrics Journal, 1, 23-46.
  • Black, F. (1976). Studies of stock prices volatility changes, American Statistical Association, 177-181.
  • Bollerslev, T., Chou, R. Y., & Kroner, K. F. (1992). ARCH modelling in finance: A review of the theory and empirical evidence, Journal of Economerics, 52, 5-59.
  • Bollerslev, T. (1986). Generalized autoregressive conditional heteroskedasticity, Journal of Econometrics, 31(3), 307-327.
  • Bolstad, William M. (2004). Introduction to bayesian statistics, John Wiley&Sons.
  • Carter, C.K., R. Kohn. (1994). On gibbs sampling for state space models, Biometrika, 81, 541-553.
  • Chernozhukov, V., Hong, H. (2003). An MCMC approach to classical estimation. Journal of Econometrics, 115(2), 293-346.
  • Cowles, M.K., B.P.Carlin. (1996). Markov chain monte carlo convergence diagnostics: A comparative review, Journal of the American Statistical Association, 91, 883-905.
  • Çil, N. (2015). Finansal Ekonometri, Der Yayınları. Degiannakis, S., Xekalaki, E. (2004). Autoregressive conditional heteroscedasticity (ARCH) models: A review, Quality Technology & Quantitative Management, 1(2), 271-324.
There are 10 citations in total.

Details

Primary Language English
Subjects Econometrics Theory
Journal Section Research Articles
Authors

Tuğçe Acar Kara 0000-0001-9223-0089

Early Pub Date October 30, 2024
Publication Date October 31, 2024
Submission Date February 6, 2024
Acceptance Date June 29, 2024
Published in Issue Year 2024 Volume: 9 Issue: 2

Cite

APA Acar Kara, T. (2024). CLASSICAL AND BAYESIAN APPROACH TO UNIVARIATE VOLATILITY MODELS. Akademik İzdüşüm Dergisi, 9(2), 91-111.

The publication rights of the articles accepted for publication and all kinds of copyrights in the published articles belong to the journal. No copyright is paid to the author.