Volume 7, Issue 2

The paper demonstrates global stability in a class of stochastic overlapping generations economies with increasing returns. These results are applied to the study of path dependent dynamics. In particular, for nonlinear stochastic models it is seen that persistence of the historical state and formal ergodicity may easily coincide. A new definition of path dependence is proposed that incorporates such dynamics.

This paper introduces bootstrap neural network pure significance tests for the no cointegration hypothesis against nonlinear cointegration alternatives. The theoretical properties of the tests are discussed and a Monte Carlo investigation of their small sample properties is undertaken.

This paper demonstrates how fiscal policy rules can be designed to eliminate all forms of endogenous fluctuations in a one-sector growth model with increasing returns-to-scale. When the policy rules are implemented, agents' optimal decisions depend only on the current state of the economy and not on any expected future states. This property shuts down the mechanism for expectations-driven fluctuations. The proposed policy rules ensure a globally unique and stable equilibrium, regardless of the degree of increasing returns.

The classical NBER leading indicators model was built solely within a linear framework. With recent developments in nonlinear time-series analysis, several authors have begun to examine the forecasting properties of nonlinear models in the field of forecasting business cycles. The research presented in this paper focuses on the development of a new approach to forecasting with leading indicators based on neural networks. Empirical results are presented for forecasting the Index of Industrial Production. The results demonstrate that a superior performance can be obtained relative to the classical model.

This paper corrects some points in the appendix of the paper: George Kapetanios (2003) "Bootstrap Neural Network Cointegration Tests Against Nonlinear Alternative Hypotheses", Studies in Nonlinear Dynamics & Econometrics: Vol. 7: No. 2, Article 2.

A Kalman filter for application to stationary or non-stationary time series is proposed. A major feature is a new initialisation method to accommodate non-stationary time series. The filter works on time series with missing values at any point of time including the initialisation phase. It can also be used where a state space model does not satisfy the traditional observability condition, a situation that can arise with seasonal time series.Another feature of the paper is that the Kalman filter is described in terms of the augmented moments of the state vectors, these being an aggregate of means, variances, covariances and other pertinent information. By doing this, the Kalman filter is specified without direct recourse to those relatively complex formulae for calculating associated means and variances found in traditional expositions.A computer implementation of the Kalman filter is also described where the augmented moments are treated as an object; the operations of addition and multiplication are overloaded to work on instances of this object; and a form of statistical conditioning is implemented as an operator.