BUTSTRAP-MODELS IN FINANCIAL CALCULATIONS OF ESTIMATION OF INVESTMENT PORTFOLIO
Abstract
The article considers a statistical bootstrap method, which is widely used in financial science. The formation of the bootstrap process has been studied, which gives rise to bootstrap statistics. The main types of bootstrap statistics used in the modern literature are generalized. The approaches of bootstrap usage for building a confidence set are grounded. In the bootstrap statistical data sample, the following methods are used: approximation of the standard sampling error; Bayesian correction using the bootstrap method; confidence intervals; the method of percentiles; centered bootstrap-percentile method; bootstrap-t conditions. The bootstrap method is a modification of the Monte Carlo method and we do not get new information in the bootstrap, but we reasonably use the available data based on the task. For example, a bootstrap can be used for small samples, for estimating the median, for correlations, for constructing confidence intervals, and in other situations described in the original work of Efron, where the estimates of pair correlation were considered. Unlike the historical modeling method, in the bootstrap method, not one trajectory of price scenarios is considered, but a large number of scenarios, in this case, the accuracy of calculations increases. In world practice, it is determined that the bootstrap method is the most applicable method of calculating the Value at Risk (VaR) indicator – the cost measure of risk. The most developed methods of the cost measure of risk are covariance, the method of historical modeling and the Monte Carlo simulation method, which will be applied in this article.
References
2. Andrews, D.W.K. (2002). Higher order improvements of a computationally attractive k-step bootstrap for extremum estimators. Econometrica 70, 119-162.
3. Andrews, D.W.K. (2004). The block-block bootstrap: Improved asymptotic refinements. Econometrica 72, 673-700.
4. Davidson R. & J.G. MacKinnon (2004). Econometric Theory and Methods. Oxford: Oxford University Press.
5. Davidson R. & J.G. MacKinnon (2006a). Bootstrap methods in econometrics. Chapter 23 of Palgrave Handbook of Econometrics, Volume 1, Econometric Theory, eds T.C. Mills & K. Patterson. London: Palgrave-Macmillan.
6. Davidson R. & J.G. MacKinnon (2006b). Bootstrap inference in a linear equation estimated by instrumental variables. Discussion Paper 1024, Queen’s University.
7. Horowitz, J.L. (2003). The bootstrap in econometrics. Statistical Science 18, 211-218.
8. Politis, D.N. (2003). The impact of bootstrap methods on time series analysis. Statistical Science 18, 219-230.
9. Efron B. (1979). Bootstrap methods: Another look at the jackknife. Ann. Statist. 7 1-26.
10. Donald E. Knuth. Seminumerical Algorithms, volume 2 of The Art of Computer Programming, chapter 4.2.2, page 232. Addison-Wesley, Boston, third edition, 1998.
