|
on Econometric Time Series |
| By: | Baris Soybilgen (Istanbul Bilgi University) |
| Abstract: | We propose a factor augmented neural network model to obtain short-term predictions of U.S. business cycle regimes. First, dynamic factors are extracted from a large-scale data set consisting of 122 variables. Then, these dynamic factors are fed into neural network models for predicting recession and expansion periods. We show that the neural network model provides good in sample and out of sample fits compared to the popular Markov switching dynamic factor model. We also perform a pseudo real time out of sample forecasting exercise and show that neural network models produce accurate short-term predictions of U.S. business cycle phases. |
| Keywords: | Dynamic Factor Model; Neural Network; Recession |
| JEL: | E37 E31 |
| Date: | 2017–08 |
| URL: | http://d.repec.org/n?u=RePEc:bli:wpaper:1703&r=ets |
| By: | Christian Brownlees; Geert Mesters |
| Abstract: | Large economic and financial panels often contain time series that influence the entire cross-section. We name such series granular. In this paper we introduce a panel data model that allows to formalize the notion of granular time series. We then propose a methodology, which is inspired by the network literature in statistics and econometrics, to detect the set of granulars when such set is unknown. The influence of the i-th series in the panel is measured by the norm of the i-th column of the inverse covariance matrix. We show that a detection procedure based on the column norms allows to consistently select granular series when the cross-section and time series dimensions are large. Importantly, the methodology allows to consistently detect granulars also when the series in the panel are influenced by common factors. A simulation study shows that the proposed procedures perform satisfactorily in finite samples. Our empirical studies demonstrate, among other findings, the granular influence of the automobile sector in US industrial production. |
| Keywords: | granularity, network models, factor models, panel data, industrial produc- tion, CDS spreads |
| JEL: | C33 C38 |
| Date: | 2017–09 |
| URL: | http://d.repec.org/n?u=RePEc:bge:wpaper:991&r=ets |
| By: | David E. Allen (School of Mathematics and Statistics, University of Sydney, Centre for Applied Finance, University of South Australia, and School of Business and Law, Edith Cowan University.); Michael McAleer (Department of Quantitative Finance National Tsing Hua University, Taiwan and Econometric Institute Erasmus School of Economics Erasmus University Rotterdam, The Netherlands and Department of Quantitative Economics Complutense University of Madrid, Spain And Institute of Advanced Sciences Yokohama National University, Japan.) |
| Abstract: | The purpose of the paper is to explore the relative biases in the estimation of the Full BEKK model as compared with the Diagonal BEKK model, which is used as a theoretical and empirical benchmark. Chang and McAleer [4] show that univariate GARCH is not a special case of multivariate GARCH, specifically, the Full BEKK model, and demonstrate that Full BEKK which, in practice, is estimated almost exclusively, has no underlying stochastic process, regularity conditions, or asymptotic properties. Diagonal BEKK (DBEKK) does not suffer from these limitations, and hence provides a suitable benchmark. We use simulated financial returns series to contrast estimates of the conditional variances and covariances from DBEKK and BEKK. The results of non-parametric tests suggest evidence of considerable bias in the Full BEKK estimates. The results of quantile regression analysis show there is a systematic relationship between the two sets of estimates as we move across the quantiles. Estimates of conditional variances from Full BEKK, relative to those from DBEKK, are lower in the left tail and higher in the right tail. |
| Keywords: | DBEKK, BEKK, Regularity Conditions, Asymptotic Properties, Non-Parametric, Bias, Qantile regression. |
| JEL: | C13 C21 C58 |
| Date: | 2017–07 |
| URL: | http://d.repec.org/n?u=RePEc:ucm:doicae:1722&r=ets |
| By: | Dumitru, Ana-Maria; Holden, Tom |
| Abstract: | The run-up to the Greek default featured marked increases in the cost of insuring sovereign debt from almost all European countries. One explanation is that market participants believed a default in one country might increase the risk of a future default in another, and so news about one country could impact all others. To test for such dynamic contagion between credit related events in different countries, we develop a procedure for tractably estimating high-dimensional Hawkes models using credit default swap prices. Unlike the prior literature, we are able to perform this estimation via maximum likelihood, even without observing events. We escape the curse of dimensionality by modelling a market portfolio of risk across countries. We find significant spillovers in credit risk between countries, with Spain, Portugal and Greece driving events in the other countries considered. |
| Keywords: | sovereign CDS spreads,credit risk,multivariate self-exciting point process,systemic risk |
| JEL: | C58 G12 |
| Date: | 2017 |
| URL: | http://d.repec.org/n?u=RePEc:zbw:esconf:168431&r=ets |
| By: | Fries, Sébastien; Zakoian, Jean-Michel |
| Abstract: | Noncausal autoregressive models with heavy-tailed errors generate locally explosive processes and therefore provide a natural framework for modelling bubbles in economic and financial time series. We investigate the probability properties of mixed causal-noncausal autoregressive processes, assuming the errors follow a stable non-Gaussian distribution. We show that the tails of the conditional distribution are lighter than those of the errors, and we emphasize the presence of ARCH effects and unit roots in a causal representation of the process. Under the assumption that the errors belong to the domain of attraction of a stable distribution, we show that a weak AR causal representation of the process can be consistently estimated by classical least-squares. We derive a Monte Carlo Portmanteau test to check the validity of the weak AR representation and propose a method based on extreme residuals clustering to determine whether the AR generating process is causal, noncausal or mixed. An empirical study on simulated and real data illustrates the potential usefulness of the results. |
| Keywords: | Noncausal process, Stable process, Extreme clustering, Explosive bubble, Portmanteau test. |
| JEL: | C13 C22 C52 C53 |
| Date: | 2017–09 |
| URL: | http://d.repec.org/n?u=RePEc:pra:mprapa:81345&r=ets |