Martin Wagner

Estimating cointegrated systems using subspace algorithms

The properties of the so-called subspace algorithms, up to now used almost only for stationary processes, are investigated in the context of cointegrated processes of order 1. It is shown for one of these algorithms that it can be adapted to deliver consistent estimates of all system parameters in the case of general I(1) VARMA models and mild conditions on the underlying noise. Estimates of the cointegrating space are derived and several test procedures for the cointegrating rank are proposed. Consistent estimation of the system order is also discussed. A simulation study shows the usefulness of subspace algorithms for estimation of and testing in cointegrated systems.

The Environmental Kuznets Curve: Exploring a Fresh Specification

Abstract The objective of this paper is primarily methodological. Using a new specification, we reanalyze the data on worldwide environmental quality investigated by Gene Grossman and Alan Krueger in their well-known paper on the environmental Kuznets curve (which postulates an inverse U-shaped relationship between income level and pollution). This new specification avoids using nonlinear transformations of potentially nonstationary regressors in panel estimation, which is a major unresolved econometric problem plaguing much of the existing literature. We furthermore draw conclusions from fixed effects estimation, which had eluded Grossman and Krueger. Our estimation results indicate the presence of an EKC for only six of the fourteen pollutants, whereas Grossman and Krueger find support for all but one pollutant.

Finite Sample Correction Factors for Panel Cointegration Tests

In this paper we present finite T mean and variance correction factors and corresponding response surface regressions for the panel cointegration tests presented in Pedroni (1999, 2004), Westerlund (2005), Larsson et al. (2001), and Breitung (2005). For the single equation tests we consider up to 12 regressors and for the system tests vector autoregression dimensions up to 12 variables. All commonly used specifications for the deterministic components are considered. The time dimension sample sizes are 10, 20, 30, 40, 50, 60, 70, 80, 90, 100, 200, 500.