Statistik und Ökonometrie

Combining the barycentric approximation with decomposition schemes to solve multistage stochastic programs

Price dynamics in electricity spot markets

Description: 

We propose a novel regime-switching approach for the simulation of electricity spot prices that is inspired by the class of fundamental models and takes into account the relation between spot and forward prices. Additionally the model is able to reproduce spikes and negative prices. Market prices are derived given an observed forward curve. We distinguish between a base regime and an upper as well as a lower spike regime. The model parameters are calibrated using historical hourly price forward curves for EEX Phelix and the dynamic of hourly spot prices. We further evaluate different time series models such as ARMA and GARCH that are usually applied for modeling electricity prices and conclude a better performance of the proposed regime-switching model.

Extreme spillover between shadow banking and regular banking

Description: 

The current financial crisis brought light to a large banking sector that existed for decades within the "darkness" of the financial system - the shadow banking sector. Shadow bank assets are widely traded in the financial markets and shadow banking activities are intertwined with the daily business of regular banks. This unregulated banking sector has become systematically important. Its failure affected the entire banking system. We present a model based on multivariate extreme value theory, which allows us to measure crashes and liquidity squeezes. Using the stable tail dependence structure, we measure the interdependency between the tail probabilities of the regular banking sector and the shadow banking sector. This allows us to calculate the conditional spillover likelihood between asset returns and liquidity spreads for selected crash levels. The empirical results indicate a fairly strong contagion probability between shadow bank assets and regular bank assets.

Stress-testing for portfolios of commodity futures

Description: 

In this paper, we perform stress-testing for a portfolio of commodity futures which mimics the dynamics of the DJ-UBS index. We identify extreme events that impacted commodity prices over time and look at correlation structures in a dynamic way, with copula functions. In line with Basel III financial regulations, we derive baseline, historical, and hybrid scenarios and discussed their advantages and shortfalls. We find that the financialization of commodity markets led to an increase in correlations and in the probability for joint extremes. However, we identify structural breaks in commodity markets that temporarily led to a breakdown of expected statistical patterns and of traditional dependence structures among commodities. This fact shows the need for forward-looking stress testing techniques, like hybrid and hypothetical scenarios, as encouraged by financial regulators.

Extreme Value Theory for Heavy-Tails in Electricity Prices

Description: 

Typical characteristics of electricity day-ahead prices at EPEX are the very high volatility and a large number of extreme price changes. In this paper, we look at hourly spot prices at the German electricity market and apply extreme value theory (EVT) to investigate the tails of the price change distribution. Our results show the importance of delimiting price spikes and modeling them separately from the core of the price distribution. In particular, we get a realistic fit of the generalized Pareto distribution (GPD) to AR-GARCH filtered price change series, and based on this model accurate forecasts of extreme price quantiles are obtained. Generally, our results suggest EVT to be of interest for both risk managers and portfolio managers in the highly volatile electricity market.

Joint Dynamics of American and European oil prices

Description: 

This chapter examines the dynamic relationship between two major international oil benchmarks, namely West Texas Intermediate (WTI) and Brent, as reference crudes for the American and European market, respectively. We provide background information on crude oil markets, including factors driving oil prices and historical events that affected the prices during the sample period. In a GARCH multivariate framework, we find that WTI is more responsive to market shocks than Brent, which enforces its position as a leading benchmark for crude oil pricing. Moreover, the conditional correlation between the benchmarks is rather high, with partly severe variations. The increased prices volatility causes the disconnections between the markets and thus downward spikes in the conditional correlation between WTI and Brent are observed. Second, we use cointegration analysis to investigate the co-movements of the Brent and WTI price series. The causality between the price series is predominantly bi-directional with slightly overwhelming influence of WTI over Brent. In the long-run, these two oil markets are unified rather than regionalized. In the short-run, however, these markets tend towards regionalization.

Structural model for electricity forward prices

Description: 

Structural models for forward electricity prices are of great relevance nowadays, given the major structural changes in the market due to the increase of renewable energy in the production mix. In this study, we aim at understanding the dynamics of the risk premium (the drift in the dynamics) and the noise (non-Gaussian, stochastic volatility) in futures prices for electricity. We firstly extract the information from smoothed price forward curves. Since electricity is largely non-storable, there is no cost-of-carry relationship linking spot and forward prices. We therefore fit our model directly to the current forward prices. The main innovation of our approach is that we aim at understanding the dynamics of risk premia and noise bi-dimensionally: in time, for one specific maturity, but also cross-section looking at the correlations in the noise between different points on the price forward curve.

A fully parametric approach for solving quantile\\ regressions with time-varying coefficients

Stress-testing for portfolios of commodities : 5th International Disaster and Risk Conference IDRC 2014, Davos

Stress-testing for portfolios of commodities

Seiten

Le portail de l'information économique suisse

© 2016 Infonet Economy

RSS - Statistik und Ökonometrie abonnieren