Article

A Structured VAR for Denmark under Changing Monetary Regimes.

Journal of Business and Economic Statistics (Impact Factor: 2.32). 10/1998; 16(4):400-411. DOI: 10.1080/07350015.1998.10524780
Source: RePEc

ABSTRACT Using recently developed statistical tools for analyzing cointegrated I(2) data, this article models money, income, prices, and interest rates in Denmark. The final model describes the dynamic adjustment to short-run changes of the process, to deviations from long-run steady states, and to several political interventions. It provides new insights about the effects of the liberalization of trade and capital in a small open European economy.

0 Bookmarks
 · 
86 Views
  • [Show abstract] [Hide abstract]
    ABSTRACT: Perhaps for the first time, this paper applies Johansen and Juselius’ methods of the cointegrated vector autoregression (VAR) model to a monthly US system of markets for soybeans, soy meal, and soy oil. Analysis of the error correction or cointegration space illuminates the empirical nature of policy-relevant market elasticities, and of effects of important policy, market, and institutional events on US soy-related markets. A statistically strong US demand for soybeans emerged as the primary cointegrating relation in the error-correction space.
    Acta Agriculturae Scandinavica Section C - Economy 06/2006; 3(2):81-98. DOI:10.1080/16507540600997430
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We apply a novel approach to study the impact of different shocks on the price level within a classical dichotomy model (Lucas, 1982) modified to account for successive shifts at known dates in the monetary policy regime. This was first driven by currency, later by the exchange rate and finally by an inflation target. The result is a CVAR with constant long-run parameters but a regime-dependent matrix of adjustment coefficients. This overcomes the so-far elusive challenge of explaining, within a single theoretical framework, inflation in Mexico since the country abandoned the gold standard. The model encompasses known results, offers new insights and clarifies decades-old misunderstandings on key aspects of the inflationary process such as inflation inertia, the role of money, the exchange rate pass-through and the impact profile of other variables. Differently from other inflation models estimated for long periods (e.g., Hendry, 2001, for the UK), ours is very parsimonious and it does not require inflation lags nor dummies for outliers. It displays a very good out-of-sample forecasting performance. It is also a straightforward example of when and how nonstructural parameters shift in response to policy changes. This provides a new explanation for why the Lucas critique has found no empirical support, with the same econometric techniques (e.g., cointegration analysis) that have been used to reject it.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We apply a novel approach to study the impact of different shocks on the price level within a classical dichotomy model (Lucas, 1982) modified to account for successive shifts at known dates in the monetary policy regime. This was first driven by currency, later by the exchange rate and finally by an inflation target. The result is a CVAR with constant long-run parameters but a regime-dependent matrix of adjustment coefficients. This overcomes the so-far elusive challenge of explaining, within a single theoretical framework, inflation in Mexico since the country abandoned the gold standard. The model encompasses known results, offers new insights and clarifies decades-old misunderstandings on key aspects of the inflationary process such as inflation inertia, the role of money, the exchange rate pass-through and the impact profile of other variables. Differently from other inflation models estimated for long periods (e.g., Hendry, 2001, for the UK), ours is very parsimonious and it does not require inflation lags nor dummies for outliers. It displays a very good out-of-sample forecasting performance. It is also a straightforward example of when and how nonstructural parameters shift in response to policy changes. This provides a new explanation for why the Lucas critique has found no empirical support, with the same econometric techniques (e.g., cointegration analysis) that have been used to reject it.