Band 15, Heft 4

The implementation of appropriate statistical techniques (backtesting) for monitoring conditional VaR models is the mechanism used by financial institutions to determine the severity of departures of the VaR model from market results and subsequently, the tool used by regulators to determine the penalties imposed for inadequate risk models. So far, however, there has been no attempt to determine the timing of this rejection and with it to obtain some guidance regarding the cause of failure in reporting an appropriate VaR. This paper corrects this by proposing U-statistic type processes that extend standard CUSUM statistics widely employed for change-point detection. In contrast to CUSUM statistics these new tests are indexed by certain weight functions that enhance their statistical power to detect the timing of the market risk model failure. These tests are robust to estimation risk and can be devised to be very sensitive to detection of market failure produced early in the out-of-sample evaluation period, in which standard methods usually fail due to the absence of data.

We propose a new class of Markov-switching models useful for business cycle analysis, with transition probabilities following independent beta autoregressive processes. We study the effects of the autoregressive dynamics on the regime duration. We propose a full Bayesian inference approach and particular attention is paid to the parameters of the latent beta autoregressive processes. We discuss the choice of the prior distributions and propose a Markov-chain Monte Carlo algorithm for estimating both the parameters and the latent variables. Finally, we provide an application to the Euro area business cycle.

In this paper, a computationally robust simulation estimator is proposed for the dynamic panel Tobit model with large categories of dependence structures. The maximum simulated likelihood estimators are obtained through a recursive algorithm formulated by Geweke-Hajivassiliou-Keane and Gibbs sampling simulators. Monte Carlo experiments indicate that the proposed robust simulation estimators perform well under the errors having a heavy-tailed distribution, even for a small simulation size. The initial conditions problem is also investigated for the robust simulation estimators through Monte Carlo experiments.

In this paper, we propose a test statistic to determine the cointegration rank of VAR processes in panel data allowing for cross-section dependence among the time series in the panel data. The cross-section dependence is accounted for through the specification of an approximate common factor model, which covers situations where there is cointegration among the cross-section dimension. Finite sample performance is investigated via a Monte Carlo experiment. We show that in some cases not accounting for common factors when they are present can lead to overestimating the cointegrating rank. We apply our proposed tests to two empirical applications and find strong evidence for panel cointegration once common factors are accounted for.

In this paper, we show how we can apply the existing theory when a parameter is on a boundary (see Andrews (1999, 2000) and Iglesias and Linton (2007)) in the context of weak instruments. When we have a priori knowledge of the signs of the relationships between the instruments and the endogenous variables, we can construct constrained k-class estimators (a special case is a constrained 2SLS estimator), where the asymptotic theory in the presence of weak instruments changes in relation to the traditional weak-instrument asymptotics of the unconstrained k-class estimators of Staiger and Stock (1997). We show theoretically and in a simulation study the advantages that we have by constraining the estimator.

Physical capital accumulation, knowledge formation and R&D-based technological progress are considered the three main sources of growth. The common view is that they characterize, in a temporal order, the three phases that a typical advanced economy passes through in its development process. Recently it has been argued, however, that an innovation-education sequence could agree better than an education-innovation transition with the empirical fact that the rise in formal education to the masses follows rather than precedes the process of industrialization. Accordingly, this paper devises an endogenous growth model with physical capital, human capital and R&D that, unlike previous related work, is able to generate adjustment dynamics in which the innovative stage precedes knowledge formation, consistent with empirical evidence.