The relationships between real wages, output per capita, inflation and unemployment in Italy between 1970 and 1994, are modelled using a cointegrated vector autoregression. There is evidence of a change in the underlying equilibria and in the dynamic evolution of the variables, probably...

The relationship between wages, prices, productivity, inflation and unemployment in Italy, Poland, and the UK between the 1960s and the early 1990s is modelled as a cointegrated vector autoregression subject to regime shifts. For each of these economies there is clear evidence of a change in the...

The value of selecting the best forecasting model as the basis for empirical economic policy analysis is questioned. When no model coincides with the data generation process, non-causal statistical devices may provide the best available forecasts: examples from recent work include intercept...

This paper considers the implications of structural breaks, such as have occurred in many transition economies, for econometric modelling based on the multivariate cointegration paradigm. It outlines recent developments on the identification of linear cointegrated systems, discusses some...

Models based on economic theory have serious problems at forecasting exchange rates better than simple univariate driftless random walk models, especially at short horizons. Multivariate time series models suffer from the same problem. In this paper, we propose to forecast exchange rates with a...

We propose a new approach to forecasting the term structure of interest rates, which allows to efficiently extract the information contained in a large panel of yields. In particular, we use a large Bayesian Vector Autoregression (BVAR) with an optimal amount of shrinkage towards univariate AR...