All new papers
http://lists.repec.org/mailman/listinfo/nep-all
All new papers2014-09-08Walter FrischModel uncertainty in panel vector autoregressive models
http://d.repec.org/n?u=RePEc:str:wpaper:1408&r=ore
We develop methods for Bayesian model averaging (BMA) or selection (BMS) in Panel Vector Autoregressions (PVARs). Our approach allows us to select between or average over all possible combinations of restricted PVARs where the restrictions involve interdependencies between and heterogeneities across cross-sectional units. The resulting BMA framework can find a parsimonious PVAR specification, thus dealing with overparameterization concerns. We use these methods in an application involving the euro area sovereign debt crisis and show that our methods perform better than alternatives. Our findings contradict a simple view of the sovereign debt crisis which divides the euro zone into groups of core and peripheral countries and worries about financial contagion within the latter group.Gary Koop, Dimitris Korobilis2014-08Bayesian model averaging, stochastic search variable selection, financial contagion, sovereign debt crisisReview of the Stochastic Properties of CO2 Futures Prices
http://d.repec.org/n?u=RePEc:ipg:wpaper:2014-565&r=ore
In this paper, we review the extant mathematical and environmental economics literatures on the stochastic properties of CO2 emission allowance futures prices. We explain the main findings arising from this literature from both continuous- and jump-diffusion models. Based on the Activity Signature Fuction by Todorov and Tauchen (2010,2011), our review shows that the Brownian motion shall be dismissed when modeling CO2 futures, in sharp contrast with the bulk of previous literature on this topic. The central result is that the evolution of the carbon futures price can be described in terms of a pure jump-diffusion process. For instance, important cases of informational shocks leading to allowance price jump can be addressed when modeled as an appropriately sampled, centered Lévy or Poisson process.Julien Chevallier2014-08-29Carbon Price; Stochastic Modeling; Activity Signature Function.Risk Spillovers across the Energy and Carbon Markets and Hedging Strategies for Carbon Risk
http://d.repec.org/n?u=RePEc:ipg:wpaper:2014-552&r=ore
This study examines the risk spillovers between energy futures prices and Europe-based carbon futures contracts. We use a Markov regime-switching dynamic correlation, generalized autoregressive conditional heteroscedasticity (MSDCC- GARCH) model in order to capture the time variations and structural breaks in the spillovers. We further evaluate the optimal weights, hedging effectiveness, and dynamic hedging strategies for the MS-DCC-GARCH model based on both the regime dependent and regime independent optimal hedge ratios. We finally complement our analysis by examining the in- and out-of sample hedging performances for alternative strategies. Our results mainly show significant volatility and time-varying risk transmission from energy markets to carbon market. We also find that spot and futures segments of the emission markets exhibit time-varying correlations and volatile hedging effectiveness. These results have important investment and policy implications.Mehmet Balcılar, Rıza Demirer, Shawkat Hammoudeh, Duc Khuong Nguyen2014-08-29Multivariate regime-switching; time-varying correlations; hedging; CO2 allowance prices.Is regularization necessary? A Wald-type test under non-regular conditions
http://d.repec.org/n?u=RePEc:unm:umagsb:2014025&r=ore
We study hypotheses testing in the presence of a possibly singular covariance matrix. We propose an alternative way to handle possible non-regularity in a covariance matrix of a Wald test, using the identity matrix as the weighting matrix when calculating the quadratic form. The resulting test statistic is not pivotal, but its asymptotic distribution can be approximated using bootstrap methods. In order to prove the validity of the approximations, we show that the square root of a positive semi-definite matrix is a continuously differentiable transformation with respect to the elements of the matrix. This result is important for the continuous mapping theorem to be applicable. We use two types of approximations. The first uses the parametric bootstrap and draws from the asymptotic distribution of the restriction with an estimated covariance matrix. The second applies the residual bootstrap to obtain the distribution of the test and delivers critical values, which control size and show good empirical power even in small samples. In contrast to regularization approaches, the test statistic considered in this paper does not involve arbitrary truncation parameters for which no practical guidelines are available and does not modify the information in the data.Duplinskiy A.2014Hypothesis Testing: General; Statistical Simulation Methods: General; Multiple or Simultaneous Equation Models: Time-Series Models; Dynamic Quantile Regressions; Dynamic Treatment Effect Models;Order Placement in a Continuous Double Auction Agent Based Model
http://d.repec.org/n?u=RePEc:mar:magkse:201443&r=ore
Modeling intraday financial markets by means of agent based models requires an additional building block which reflects the order execution, i.e. the trading process. Current implementations rely only on stochastic placement strategies, ranging from total randomness to adding some budget constraints. This contribution addresses the issue of order placement for low-tech traders, by replacing the zero-intelligence assumption with a microtrading-based approach. The results show that the power-law decaying relative price distribution of off-spread limit orders and the concave shape of the overall market price impact can be replicated when rational order submission strategies are used.Alexandru Mandes2014agent based modeling, high-frequency financial markets, continuous double auction, order placement, market impactMacroeconomies as Constructively Rational Games
http://d.repec.org/n?u=RePEc:isu:genres:37834&r=ore
Real-world decision-makers are forced to be locally constructive, in the sense that their actions are constrained by the interaction networks, limited information, and computational capabilities at their disposal.� This study poses the following question:� Suppose utility-seeking consumers and profit-seeking firms in an otherwise standard dynamic macroeconomic model are required to be locally constructive decision-makers, unaided by the external imposition of global coordination conditions.� What combinations of locally constructive decision rules result in good macroeconomic performance relative to a social planner benchmark model, and what are the game-theoretic properties of these decision-rule combinations?� We begin our investigation of this question by specifying locally constructive decision rules for the consumers and firms that range from simple reinforcement learning to sophisticated adaptive dynamic programming algorithms.� We then use computational experiments to explore macroeconomic performance under alternative decision-rule combinations.� A key finding is that simpler rules can outperform more sophisticated rules, but that forward-looking behavior coupled with a relatively long memory permitting past observations to inform current decision-making is critical for good performance.Sinitskaya, Ekaterina, Tesfatsion, Leigh2014-08-22Learning; Macroeconomics; agent-based; game; stochastic optimizationConstant Proportion Portfolio Insurance Effectiveness with Transaction Costs
http://d.repec.org/n?u=RePEc:ipg:wpaper:2014-509&r=ore
In this paper, we examine main properties of the Constant Proportion Portfolio Insurance (CPPI) strategy, when trading in continuous-time is not allowed. We focus instead on stochastic-time rebalancing. We prove that investor's tolerance determines crucially portfolio performance, in particular when taking transaction costs into account. We illustrate this feature in the geometric Brownian case and we provide some numerical insights in this framework.Farid Mkaouar, Jean-Luc Prigent2014-08-29Portfolio insurance; CPPI with transaction cost; ToleranceCombining distributions of real-time forecasts: An application to U.S. growth
http://d.repec.org/n?u=RePEc:unm:umagsb:2014027&r=ore
We extend the repeated observations forecasting ROF analysis of Croushore and Stark 2002 to allow for regressors of possibly higher sampling frequencies than the regressand. For the U.S. GNP quarterly growth rate, we compare the forecasting performances of an AR model with several mixed-frequency models among which is the MIDAS approach. Using the additional dimension provided by different vintages we compute several forecasts for a given calendar date and subsequently approximate the corresponding distribution of forecasts by a continuous density. Scoring rules are then employed to construct combinations of them and analyze the composition and evolvement of the implied weights over time. Using this approach, we not only investigate the sensitivity of model selection to the choice of which data release to consider, but also illustrate how to incorporate revision process information into real-time studies. As a consequence of these analyses, weintroduce a new weighting scheme that summarizes information contained in the revision process of the variables under consideration.Götz T.B., Hecq A.W., Urbain J.R.Y.J.2014Single Equation Models; Single Variables: Models with Panel Data; Longitudinal Data; Spatial Time Series; Forecasting and Prediction Methods; Simulation Methods ;