Search results

1

Wyznaczanie VaR przy pomocy łańcucha Markowa

100%

Stawicki J.

Studia Ekonomiczne

|

2018

|

vol. 364

153-166

PL

Artykuł przedstawia możliwości wykorzystania łańcuchów Markowa do określania wartości zagrożonej. W określaniu VaR preferuje się metodę kwantyli warunkowych. Prosta metoda konstrukcji modelu łańcucha Markowa poprzez określenie stanów oraz szacowanie macierzy prawdopodobieństw przejść wpisuje się w tę preferowaną metodę. Wyznaczenie VaR następuje poprzez wybór modelu łańcucha Markowa przy znajomości bieżącej stopy zwrotu.

EN

This article presents the possibilities for using the Markov chains to determine the Value at Risk. In determining VaR, conditional quantiles are preferred. The simple method of constructing a Markov chain model by defining states and estimating the transition probability matrix is entered into these preferred methods.

2

Wykorzystanie warunkowego modelu maksimów blokowych do pomiaru Value at Risk

75%

Euchast K.

Studia Ekonomiczne

|

2016

|

vol. 295

19-32

PL

W pracy rozważany jest warunkowy model maksimów blokowych, wywodzący się z teorii wartości ekstremalnych. Badana jest jego przydatność do wyznaczania jednookresowych prognoz Value at Risk (VaR), gdy parametry modelu są szacowane na podstawie małej próby. Weryfikowana jest hipoteza, iż warunkowy model maksimów blokowych zwraca poprawne oszacowania VaR. Przeprowadzono empiryczną analizę poprawności modelu na siedmiu światowych indeksach giełdowych w latach 2001-2013. Badania potwierdziły, że model jest poprawny pod względem liczby i niezależności przekroczeń VaR oraz może być alternatywą dla innych często wykorzystywanych modeli.

EN

The model under consideration is conditional block maxima model. In this paper the usefulness of the model to determine one-ahead forecast VaR is taken into account, when the model parameters are estimated in small sample. The hypothesis, that conditional block maxima model is correct to estimate VaR forecasts is verified. We carried out an empirical analysis on seven world stock market indices in the years of 2001- 2013. The survey confirmed, that the model is correct in terms of number and independence of VaR exceedances and can be a good alternative to other often used models.

3

Weryfikacja historyczna modeli wartości zagrożonej – zastosowanie wybranych metod dla rynku polskiego w okresie kryzysu finansowego

71%

Lusztyn M.

Econometrics. Ekonometria. Advances in Applied Data Analytics

|

2013

|

issue 4(42)

117-129

EN

Several banks use internal Value at Risk models to measure market risk and to calculate regulatory capital necessary to cover that risk. Backtesting is a statistical tool that allows differentiating precise and imprecise risk models. The objective of this paper is to backtest selected Value at Risk models in a period preceding and during the financial crisis, based on the example of Polish currency, equity and bond markets. The obtained results do not justify unequivocal statistical acceptance of any of the analyzed models. This in turn suggest extreme caution in using Value at Risk as the only quantitative risk management tool. Stable and cautious risk management of a financial institution calls for supplementing Value at Risk with alternative risk measures.

4

Metoda oceny ryzyka realizacji oprogramowania do wspomagania działalności przedsiębiorstwa na przykładzie oprogramowania typu Open Source

71%

Kieruzel M.

Informatyka Ekonomiczna

|

2014

|

issue 1(31)

259-268

EN

The article presents the idea and design of the original method and its implementation associated with the valuation of risks in IT projects. This new method is based on the adaptation of the VaR approach. The article shows the issues of risk analysis in software production, the original proposition of risk assessment model of software projects, as well as the verification of the model. The paper takes into account in particular: high volatility of environment, multi-step nature of the activities with the participation of a large number of people, high complexity of project's tasks and the lack of risk validation in methodology for the implementation of IT projects.

5

Assessment of the size of VaR backtests for small samples

71%

Kaszyński D., Kamiński B., Pankratz B.

Przegląd Statystyczny

|

2020

|

vol. 67

|

issue 2

114-151

EN

The market risk management process includes the quantification of the risk connected with defined portfolios of assets and the diagnostics of the risk model. Value at Risk (VaR) is one of the most common market risk measures. Since the distributions of the daily P&L of financial instruments are unobservable, literature presents a broad range of backtests for VaR diagnostics. In this paper, we propose a new methodological approach to the assessment of the size of VaR backtests, and use it to evaluate the size of the most distinctive and popular backtests. The focus of the paper is directed towards the evaluation of the size of the backtests for small-sample cases – a typical situation faced during VaR backtesting in banking practice. The results indicate significant differences between tests in terms of the p-value distribution. In particular, frequency-based tests exhibit significantly greater discretisation effects than duration-based tests. This difference is especially apparent in the case of small samples. Our findings prove that from among the considered tests, the Kupiec TUFF and the Haas Discrete Weibull have the best properties. On the other hand, backtests which are very popular in banking practice, that is the Kupiec POF and Christoffersen’s Conditional Coverage, show significant discretisation, hence deviations from the theoretical size.

6

Hybrid Concepts of Long-Term Estimates for Value at Risk

71%

Mentel G.

Folia Oeconomica Stetinensia

|

2008

|

vol. 7

|

issue 1

1-12

EN

There is a growing demand for models which enable to measure and assess the risk in long-term horizons (sometimes more than 2 years). The practical demand for such models is required by the institutions which manage the investments and retirement funds. In the paper the theoretical aspects of risk assessment methodology with the use of Value at Risk (VaR) were presented. In this method in order to estimate the long-term VaR limits the hybrid model which is the optimum mixture of random walk and mean reversion was used. The application of the presented methodology was exemplified by the estimation of long-term predictions for VaR limits for stock prices.

7

Modelling extreme market risk of polish banks’ debt instruments’ portfolios

71%

Łupiński M.

Econometrics. Ekonometria. Advances in Applied Data Analytics

|

2013

|

issue 3(41)

113-130

EN

The main goal of this article is to present extreme market risk evaluation methods which go beyond the standard Value at Risk methodology. Two main approaches: Expected Tail Loss (ETL) and Extreme Value Theory (EVT) are presented and then applied to simulate interest risk stemming from government debt portfolio held by Polish banks. The two methods seem to be very useful to estimate real market risk exposures during the times of distress on the financial markets.

8

Estimation of Value at Risk: extreme value and and robust approaches

71%

TRZPIOT G., MAJEWSKA J.

Operations Research and Decisions

|

2010

|

vol. 20

|

issue 1

132-143

EN

The large portfolios of traded assets held by many financial institutions have made the measurement of market risk a necessity. In practice, VaR measures are computed for several holding periods and confidence levels. A key issue in implementing VaR and related risk measures is to obtain accurate estimates for the tails of the conditional profit and loss distribution at the relevant horizons. VaR forecasts can be heavily affected by a few influential points, especially when long forecast horizons are considered. Robustness can be enhanced by fitting a generalized Pareto distribution to the tails of the distribution of the residual and sampling tail residuals from this density. However, to ensure a sufficiently large breakdown point for the estimator of the generalized Pareto tails, robust estimation is needed (see Dell’Aquila, Ronnchetti, 2006). The aim of the paper is to compare selected approaches to computing Value at Risk. We consider classical and robust conditional (GARCH) and unconditional (EVT) semi-nonparametric models where tail events are modeled using the generalized Pareto distribution. We wish to answer the question of whether the robust semi-nonparametric procedure generates more accurate VaRs than the classical approach does.

9

Review of Value at Risk estimation methods

71%

Stefaniak R.

Prace Naukowe Uniwersytetu Ekonomicznego we Wrocławiu

|

2018

|

issue 519

173-183

XX

On a daily basis, managers in risk management teams use a number of methods to manage various types of risk. One of the most popular methods of measuring market risk is Value at Risk. Estimation of Value at Risk gives a possibility to determine a loss, which can occur or can be exceeded with a given probability and tolerance level. Moreover, this measure of risk shows in just one number entire risk of the portfolio. In addition, various methods and probability distributions can be used to estimate Value at Risk. A goal of this paper is the evaluation of Value at Risk estimation methods on the basis of backtesting results. In the empirical part, the data for 4 investment portfolios was used. The portfolios were diversified in terms of geographic location of firms that were taken into consideration.

10

WHAT KIND OF SYSTEMIC RISKS DO WE FACE IN THE EUROPEAN BANKING SECTOR? THE APPROACH OF CoVaR MEASURE

71%

Karkowska R.

Faculty of Management Working Paper Series

|

2015

|

issue WPS 1/2015

1-15

XX

We measure a systemic risk faced by European banking sectors using the CoVaR measure. We propose the conditional value-at-risk (CoVaR) for measuring a spillover risk which demonstrates the bilateral relation between the tail risks of two financial institutions. The aim of the study is to estimate the contribution systemic risk of the bank i in the analyzed banking sector of a country in conditions of its insolvency. The study included commercial banks from 8 emerging markets from Europe, which gave a total of 40 banks, traded on the public market, which provided a market valuation of the bank's capital. The conclusions are that the CoVaR seems to be a better measure for systemic risk in the banking sector than the VaR, which is more individual. And banks in developing countries in Europe do not provide significant risk for the banking sector as a whole. But it must be taken into account that some individuals that may find objectionable. Our results hence tend to a practical use of the CoVaR for supervisory purposes.

11

Wykorzystanie modeli GARCH w analizie ryzyka finansowego spółek akcyjnych notowanych na GPW

62%

Szczerbak G.

Optimum. Studia Ekonomiczne

|

2017

|

vol. 3(87)

PL

Celem niniejszego artykułu jest odpowiedź na pytanie, czy możliwe jest skuteczne prognozowanie wartości ryzyka rynkowego w warunkach polskiego rynku kapitałowego. Do analizy tego zagadnienia wykorzystano szeregi dziennych stóp zwrotu spółek notowanych na Giełdzie Papierów Wartościowych w Warszawie w latach 2000-2015. W części badawczej pracy przyjęto założenie, iż analizowane szeregi czasowe są realizacją procesu GARCH, co pozwoliło na modelowanie charakterystycznych właściwości spotykanych w empirycznych szeregach czasowych stóp zwrotu akcji giełdowych. Pomiaru ryzyka dokonano posługując się popularnymi miarami zagrożenia. Została również podjęta próba wyboru optymalnej spośród najpopularniejszych metod estymacji ryzyka.

EN

The aim of this paper is to investigate whether it is possible to successfully forecast market risk in the Polish capital market. To answer this question, daily time series of the stock prices listed on the Warsaw Stock Exchange between 2000-2015 are analysed. In the research part of the paper, it is assumed that the analysed time series are the realisation of the GARCH process, which allows the author to model the characteristic properties among the empirical data. The risk is assessed with the use of popular quantile risk measures. Additionally, an attempt is made to establish the optimal method of risk estimation.

12

The optimal portfolio in respect to Expected Shortfall: a comparative study.

62%

Gurgul H., Machno A., Syrek R.

Managerial Economics

|

2013

|

vol. 14

17-38

EN

Value at Risk plays a crucial role in the risk management. However, this risk measure has some drawbacks. The alternative risk measure is Expected Shortfall, which is rarely used, but exhibits desirable properties. In the paper, the estimation of both risk measures has been conducted, for pairs of index returns (DJIA, DAX, ATX), based on Markowitz model, the regime switching copula model and the multivariate GARCH model. The results suggest that a misspecification can cause many errors. Incorrect models cause bias of mean, especially models which do not as- sume dynamic structure of the market Both an underestimation and an overestimation of a risk has been observed. In the paper, it is shown that the measure of change in Expected Shortfall as a function of the expected return is strongly underestimated under the normal distribution assumption.

13

A Comparative Analysis of Value at Risk Measurement on Emerging Stock Markets: Case of Montenegro

54%

Cerović J., Lipovina-Božović M., Vujošević S.

Business Systems Research Journal

|

2015

|

vol. 6

|

issue 1

36-55

EN

Background: The concept of value at risk gives estimation of the maximum loss of financial position at a given time for a given probability. The motivation for this analysis lies in the desire to devote necessary attention to risks in Montenegro, and to approach to quantifying and managing risk more thoroughly. Objectives: This paper considers adequacy of the most recent approaches for quantifying market risk, especially of methods that are in the basis of extreme value theory, in Montenegrin emerging market before and during the global financial crisis. In particular, the purpose of the paper is to investigate whether extreme value theory outperforms econometric and quantile evaluation of VaR in emerging stock markets such as Montenegrin market. Methods/Approach: Daily return of Montenegrin stock market index MONEX20 is analyzed for the period January, 2004 - February, 2014. Value at Risk results based on GARCH models, quantile estimation and extreme value theory are compared. Results: Results of the empirical analysis show that the assessments of Value at Risk based on extreme value theory outperform econometric and quantile evaluations. Conclusions: It is obvious that econometric evaluations (ARMA(2,0)- GARCH(1,1) and RiskMetrics) proved to be on the lower bound of possible Value at Risk movements. Risk estimation on emerging markets can be focused on methodology using extreme value theory that is more sophisticated as it has been proven to be the most cautious model when dealing with turbulent times and financial turmoil.

14

Portfolio selection: method of the step by step assigned weights

54%

Pavlík M., Michalski G., Lukáčik M.

Econometrics. Ekonometria. Advances in Applied Data Analytics

|

2015

|

issue 3 (49)

78-97

EN

The authors conceived a new simple method for creating the approximation of the border of investment opportunities. The method enumerates all the possibilities of assigning weights to the investment portfolio. It does not enable short sales. The software which the authors coded is written in VBA and also enables active management. The method is simple, accurate but demanding. The authors also created a simple methodology for testing the quality of the approximation of the border of investment opportunities.

15

Monte Carlo simulation approach to calculate Value at Risk: application to WIG20 and mWIG40

54%

Pasieczna A. H.

Nauki o Finansach

|

2019

|

issue vol. 24 no. 2

61-75

EN

This paper reports our estimates of the Value at Risk using Monte Carlo simulations for which we developed a computer program. Our approach involves obtaining Monte Carlo parameters by fitting real historical data of different periods to probability distributions. We applied the algorithm to the WIG20 and mWIG40 stock indices, and performed simulations for the Value at Risk at 95% and 99% confidence intervals over six estimation periods ranging from 1 trading day to 250 trading days. This approach was evaluated using the percentage failures and the Kupiec Proportion of Failures test. Our results indicate that this method is highly influenced by the choice of past historical and estimation period lengths considered. Overall, we observed that the Monte Carlo computational scheme is a reliable method for quantifying VaR when parametrized well.

16

Teoretyczne rozkłady prawdopodobieństwa w pomiarze strat ekstremalnych na działalności inwestycyjnej przedsiębiorstwa

54%

Kaczmarzyk J., Kania P.

Studia Ekonomiczne

|

2016

|

vol. 301

125-136

PL

Działalność inwestycyjna podmiotów gospodarczych ma charakter racjonalny, gdy podejmowanym decyzjom dotyczącym alokacji wolnych środków pieniężnych towarzyszy możliwie najdokładniejszy pomiar ryzyka. Podmioty gospodarcze alokujące nadwyżki płynności na rynku finansowym są narażone na ryzyko rynkowe. Szczególnie ważnym aspektem ryzyka rynkowego są straty ekstremalne mierzone wartością zagrożoną. Część metod pomiaru skrajnego ryzyka wykorzystuje założenie o rozkładzie normalnym stóp zwrotu. Konsekwencją może być niedoszacowanie lub przeszacowanie ryzyka. Celem artykułu jest rozpatrzenie wykorzystania, innych niż normalny, teoretycznych rozkładów stóp zwrotu, wierniej odzwierciedlających rozkłady empiryczne ustalane na podstawie danych historycznych. Rozważania dotyczące rozkładów teoretycznych poparto badaniami dziennych prostych stóp zwrotu 40 funduszy inwestycyjnych funkcjonujących na polskim rynku finansowym w latach 2003-2013.

EN

The investment activity of economic entities is rational if undertaken decisions (in terms of free financial resources allocation) are preceded by possibly most accurate market risk measurement. Especially when it comes to measurement of market risk using value at risk approach. Some of extreme risk measurement methods assume normal probability distribution of returns. The consequence of such assumption can be over- or underestimation of risk. The aim of the paper is to consider the use of another than normal probability distributions. The authors assume that using another distribution may lead to more convenient results of risk measurement. The research bases on the analysis of the simple return rates of Polish investment funds in 2003-2013.

17

Ocena przydatności modeli VaR do szacowania ryzyka inwestycji na rynku metali szlachetnych

54%

Just M.

Studia Ekonomiczne

|

2016

|

vol. 295

45-59

PL

Celem pracy była analiza przydatności wybranych warunkowych modeli VaR do szacowania ryzyka inwestycji na londyńskim rynku metali szlachetnych. Zbadano przydatność wykorzystania modelu GARCH z rozkładem normalnym, t-Studenta i skośnym t-Studenta, modelu GARCH-EVT i GARCH-FHS. Szczególnie użyteczne do szacowania ryzyka inwestycji w metale szlachetne okazały się następujące modele: GARCH z rozkładem t-Studenta i GARCH-EVT niezależnie od zajmowanej pozycji na rynku metali oraz GARCH z rozkładem skośnym t-Studenta dla pozycji długiej. Modele te pozwoliły na poprawne szacowanie wartości zagrożonej na rynku metali szlachetnych w okresach największych turbulencji na tym rynku.

EN

The aim of the paper was to analyze the usefulness of selected conditional Value at Risk (VaR) models for estimating the investment risk in the London precious metals market. The usefulness of the following models: GARCH with normal distribution, Student-t distribution, skewed Student-t distribution, GARCH-EVT and GARCH-FHS was evaluated. Particularly useful for estimating the investment risk on the precious metals market proved to be the following models: GARCH with the Student-t distribution and GARCH-EVT irrespective of the position on the metals market and GARCH with skewed Student-t distribution for the long position. They enable to estimate the VaR correctly in very turbulent times on the market of precious metals.

18

Wartość zagrożona portfela inwestycyjnego szacowana na podstawie danych wysokiej częstotliwości − badania empiryczne

54%

Iskra D., Czernik T.

Studia Ekonomiczne

|

2015

|

vol. 221

32-49

PL

W opracowaniu zaprezentowano wyniki szacowania wartości zagrożonej spółek oraz optymalnych portfeli inwestycyjnych. Badania przeprowadzono na minutowych notowaniach spółek wchodzących w skład indeksu S&P100. W symulacjach uwzględniono dwa podejścia konstrukcji empirycznych rozkładów logarytmicznej stopy zwrotu użytych do wyznaczania wartości zagrożonej. W pierwszym z nich rozpatrywany szereg zawierał kolejne notowania cen akcji. W podejściu drugim w konstrukcji rozkładów empirycznych dokonano podziału dni na części i wyznaczano rozkład na podstawie danych z wybranych części dnia sesyjnego (np. z jednej godziny) z kilku, kilkunastu dni. W wyniku przeprowadzonych badań wykazano, iż w pewnych przypadkach (użyte podejście, zakres parametrów) zgodność oszacowanej wartości zagrożonej z realnymi stratami była wysoka.

EN

Paper presents results of estimating Value at Risk for stocks and the optimal investment portfolios. Study was conducted at the minute quotations of companies included in the S&P100 index. The simulations included two design approaches of empirical distributions of the logarithmic rate of return used to determine the value at risk. The first one takes into account consecutive price quotations. In the second price quotations were divided into empirical distributions days were divided into six groups (quotations which come from time interval e.g. 10 am-11 am from each consecutive day were transferred to the same data set). The research has shown that in certain cases the accuracy of the estimated value at risk of real loss was high.

19

Comparison of market risk of an equity asset class measured by Value at Risk and Maximal Loss according to Monte Carlo method with fractional Brownian motion evolution of the price and historical simulation approach

45%

Baca M.

Studia Ekonomiczne

|

2016

|

vol. 297

7-21

EN

In this paper, author provides a comparison of market risk of the six equities from the Polish stock exchange. In order to calculate the risk, quantile-based risk measures have been used: Value at Risk and Maximal Loss. Two common approaches to calculate quantile-based measures have been used: Monte Carlo simulation and historical simulation. However, for the simulation of the future paths in the Monte Carlo approach, the fractional Brownian motion has been used instead of geometric Brownian motion.

PL

W niniejszym artykule autor dokonuje analizy ryzyka rynkowego akcji giełdowych sześciu spółek z Warszawskiej Giełdy Papierów Wartościowych. Dla celów analizy zostały wybrane dwie kwantylowe miary ryzyka: wartość zagrożona ryzykiem (ang. Value at Risk, VaR) oraz maksymalna strata (ang. Maximal Loss). Analizę przeprowadzono na podstawie metody Monte Carlo oraz symulacji historycznej. Jednakże w metodzie Monte Carlo przyszłe wartości cen są dane ułamkowym ruchem Browna, a nie − jak podpowiada praktyka rynkowa − geometrycznym ruchem Browna.

20

Ekstremalne ryzyko cenowe na rynku zbóż w Polsce

45%

Just M.

Studia Ekonomiczne

|

2016

|

vol. 297

66-77

PL

Głównym celem artykułu była ocena ekstremalnego ryzyka cenowego na rynku zbóż w Polsce. Ryzyko zostało oszacowane na podstawie średnich tygodniowych cen skupu zbóż pochodzących z okresu od początku 2004 do połowy października 2014 roku. Ryzyko wyznaczono za pomocą dwóch miar: wartości zagrożonej (VaR) i oczekiwanego niedoboru (ES), wykorzystując teorię wartości ekstremalnych (EVT). Oszacowane miary ryzyka porównano z miarami otrzymanymi w wyniku zastosowania podejścia klasycznego (metody symulacji historycznej oraz wariancji-kowariancji). Wyniki badań wskazują na występowanie różnic w poziomie ekstremalnego ryzyka cenowego na rynku zbóż w Polsce.

EN

The main aim of the paper is to assess the extreme price risk on the cereals market in Poland. The risk was estimated on the basis of average weekly procurement prices of the cereals from the period of the beginning of 2004 till mid-October 2014. Two measures of risk were determined: Value at Risk (VaR) and Expected Shortfall (ES), by means of Extreme Values Theory (EVT). The estimated risk measures were compared with measures obtained with conventional methods (Historical Simulation Method, Variance-Covariance Method). The results of the analysis show the existence of differences in the level of extreme price risk on the cereals market in Poland.

Refine search results

Wyznaczanie VaR przy pomocy łańcucha Markowa

Wykorzystanie warunkowego modelu maksimów blokowych do pomiaru Value at Risk

Weryfikacja historyczna modeli wartości zagrożonej – zastosowanie wybranych metod dla rynku polskiego w okresie kryzysu finansowego

Metoda oceny ryzyka realizacji oprogramowania do wspomagania działalności przedsiębiorstwa na przykładzie oprogramowania typu Open Source

Assessment of the size of VaR backtests for small samples

Hybrid Concepts of Long-Term Estimates for Value at Risk

Modelling extreme market risk of polish banks’ debt instruments’ portfolios

Estimation of Value at Risk: extreme value and and robust approaches

Review of Value at Risk estimation methods

WHAT KIND OF SYSTEMIC RISKS DO WE FACE IN THE EUROPEAN BANKING SECTOR? THE APPROACH OF CoVaR MEASURE

Wykorzystanie modeli GARCH w analizie ryzyka finansowego spółek akcyjnych notowanych na GPW

The optimal portfolio in respect to Expected Shortfall: a comparative study.

A Comparative Analysis of Value at Risk Measurement on Emerging Stock Markets: Case of Montenegro

Portfolio selection: method of the step by step assigned weights

Monte Carlo simulation approach to calculate Value at Risk: application to WIG20 and mWIG40

Teoretyczne rozkłady prawdopodobieństwa w pomiarze strat ekstremalnych na działalności inwestycyjnej przedsiębiorstwa

Ocena przydatności modeli VaR do szacowania ryzyka inwestycji na rynku metali szlachetnych

Wartość zagrożona portfela inwestycyjnego szacowana na podstawie danych wysokiej częstotliwości − badania empiryczne

Comparison of market risk of an equity asset class measured by Value at Risk and Maximal Loss according to Monte Carlo method with fractional Brownian motion evolution of the price and historical simulation approach

Ekstremalne ryzyko cenowe na rynku zbóż w Polsce