Six-variable vector autoregressive systems consisting of macroeconomic series are investigated. parallel data series for four european countries are used: austria, germany (federal republic), finland, and the united kingdom. all data series are not seasonally adjusted. the aim of the paper is to show that most of the series are better modeled using stochastic seasonality and seasonal unit roots models than simple deterministic models of seasonal structures. as a second step, seasonal cointegration in the systems is studied. it is shown that all four economies display seasonal cointegration as well as usual cointegration.;

The causes of the wide variation in growth rates between countries have been debated by theorists of economic growth. Different studies have shown these disparities between growth rates largely to have been caused by different rates of increase in productivity per unit of factor input. The observed comovement between productivity and export growth suggest a direct link between these two variables. The paper explores the causal relationship between productivity and exports based on Austrian data using time series analysis. The causality analysis indicates no causal link from exports to productivity while the null of no causality from productivity to exports has to be rejected at conventional levels. Copyright 1989 by MIT Press.