Ivan Savin

Heuristic Model Selection for Leading Indicators in Russia and Germany

Business tendency survey indicators are widely recognised as a key instrument for business cycle forecasting. Their leading indicator property is assessed with regard to forecasting industrial production in Russia and Germany. For this purpose, vector autoregressive (VAR) models are specified and estimated to construct forecasts. As the potential number of lags included is large, we compare full-specified VAR models with subset models obtained using a Genetic Algorithm enabling “holes” in multivariate lag structures. The problem is complicated by the fact that a structural break and seasonal variation of indicators have to be taken into account. The models allow for a comparison of the dynamic adjustment and the forecasting performance of the leading indicators for both countries revealing marked differences between Russia and Germany. JEL classification: C52, C61, E37 Keywords: Leading indicators, business cycle forecasts, VAR, model selection, genetic algorithms

A Comparative Study of the Lasso-Type and Heuristic Model Selection Methods

This study presents a first comparative analysis of Lasso-type (Lasso, adaptive Lasso, elastic net) and heuristic subset selection methods. Although the Lasso has shown success in many situations, it has some limitations. In particular, inconsistent results are obtained for pairwise strongly correlated predictors. An alternative to the Lasso is constituted by model selection based on information criteria (IC), which remains consistent in the situation mentioned. However, these criteria are hard to optimize due to a discrete search space. To overcome this problem, an optimization heuristic (Genetic Algorithm) is applied. Monte-Carlo simulation results are reported to illustrate the performance of the methods.

Lasso-Type and Heuristic Strategies in Model Selection and Forecasting

Several approaches for subset recovery and improved forecasting accuracy have been proposed and studied. One way is to apply a regularization strategy and solve the model selection task as a continuous optimization problem. One of the most popular approaches in this research field is given by Lasso–type methods. An alternative approach is based on information criteria. In contrast to the Lasso, these methods also work well in the case of highly correlated predictors. However, this performance can be impaired by the only asymptotic consistency of the information criteria. The resulting discrete optimization problems exhibit a high computational complexity. Therefore, a heuristic optimization approach (Genetic Algorithm) is applied. The two strategies are compared by means of a Monte–Carlo simulation study together with an empirical application to leading business cycle indicators in Russia and Germany.

Do Firms Benefit from Complementarity Effect in R&D and What Drives Their R&D Strategy Choices?

This paper analyzes whether firms conducting internal R&D and acquiring external high-tech equipment experience a complementarity effect. For German CIS data we conduct a complete set of indirect and direct complementarity tests refining the analysis by looking at various types of innovations and industries. Complementary effects are found in the indirect but not so in the direct approach. In contrast to previous literature, we find the distinct R&D strategy choices to be significant drivers of innovative activity and we identify contextual variables explaining the joint occurrence of the two strategies.

No such thing as a perfect hammer: comparing different objective function specifications for optimal control

Linear-quadratic (LQ) optimization is a fairly standard technique in the optimal control framework. LQ is very well researched, and there are many extensions for more sophisticated scenarios like nonlinear models. Conventionally, the quadratic objective function is taken as a prerequisite for calculating derivative-based solutions of optimal control problems. However, it is not clear whether this framework is as universal as it is considered to be. In particular, we address the question whether the objective function specification and the corresponding penalties applied are well suited in case of a large exogenous shock an economy can experience because of, e.g., the European debt crisis. While one can still efficiently minimize quadratic deviations around policy targets, the economy itself has to go through a period of turbulence with economic indicators, such as unemployment, inflation or public debt, changing considerably over time. We test four alternative designs of the objective function: a least median of squares based approach, absolute deviations, cubic and quartic objective functions. The analysis is performed based on a small-scale model of the Austrian economy and illustrates a certain trade-off between quickly finding an optimal solution using the LQ technique (reaching defined policy targets) and accounting for alternative objectives, such as limiting volatility in economic performance. As an implication, we argue in favor of the considerably more flexible optimization technique based on heuristic methods (such as Differential Evolution), which allows one to minimize various loss function specifications, but also takes additional constraints into account.

Solving Nonlinear Stochastic Optimal Control Problems Using Evolutionary Heuristic Optimization

Policy makers constantly face optimal control problems: what controls allow to achieve certain targets in, e.g., GDP growth or inflation? Conventionally this is done by applying certain linear-quadratic optimization algorithms to dynamic econometric models. Several algorithms extend this baseline framework to nonlinear stochastic problems. However, those algorithms are limited in a variety of ways including, most importantly, restriction to local best solutions only and the symmetry of objective function. In Blueschke et al. (2013a) a new flexible optimization method based on Differential Evolution is suggested. It allows to lift these limitations and achieve better approximations of the policy targets, but is designed to deterministic problems only. This study extends the methodology by dealing with stochastic problems in two different ways: applying extreme event analysis and by minimizing the median objective value. Thus, this research is aimed to broaden the range of decision support information used by policy makers in choosing optimal strategy under much more realistic conditions.

Slow and Steady Wins the Race: Approximating Nash Equilibria in Nonlinear Quadratic Tracking Games Steter Tropfen höhlt den Stein: Approximation von Nash Gleichgewichten in Nicht-linearen Dynamischen Spielen

Abstract We propose a new method for solving nonlinear dynamic tracking games using a meta-heuristic approach. In contrast to ‘traditional’ methods based on linear-quadratic (LQ) techniques, this derivative-free method is very flexible with regard to the objective function specification. The proposed method is applied to a three-player dynamic game and tested versus a derivative-dependent method in approximating solutions of different game specifications. In particular, we consider a dynamic game between fiscal (played by national governments) and monetary policy (played by a central bank) in a monetary union. Apart from replicating results of the LQ-based techniques in a standard setting, we solve two ‘non-standard’ extensions of this game (dealing with an inequality constraint in a control variable and introducing asymmetry in penalties of the objective function), identifying both a cooperative Pareto and a non-cooperative open-loop Nash equilibria, where the traditional methods are not applicable. We, thus, demonstrate that the proposed method allows one to study more realistic problems and gain better insights for economic policy.

Factor-Biased Technical Change and Specialization Patterns

We analyze the medium- and long-run effects of international integration of capital markets on specialization patterns of countries. For that purpose, we incorporate induced technical change into a Heckscher-Ohlin model with a continuum of final goods. This provides a comprehensive theory that explains the dynamics of comparative advantages based on differences in effective factor endowments. Our model constitutes an appropriate framework for understanding the changes in industrial structure of foreign trade observed, e.g., in the CEE countries over the last two decades. In addition, our approach provides a theoretical foundation for the empirical prospective comparative advantage index (Savin and Winker 2009) with new insights into the future dynamics of comparative advantages. Eventually, the model may serve as a basis to set development priorities in countries being in the period of transition.