Abstract
Chen et al. (2010) report that for ‘commodity currencies’, the exchange rate predicts the country’s commodity index but not vice versa. The commodity currency hypothesis is consistent with the Engle and West (2005) exchange rate model if the fundamental is chosen to be the country’s key export prices and if
the latter are exogenous to the exchange rate dynamics. In our view, however, commodity prices are essentially financial asset prices that are set in a forward-looking way, exactly like exchange rates.
If both the exchange rate and the commodity prices are based on discounted future expectations, one should mostly observe contemporaneous correlations, not one-directional cross-predictability from one variable toward the other.
Using three different data sets and various econometric techniques, we do find the contemporaneous correlations as predicted by the financial asset view of commodity prices. Cross-predictability, in contrast, seems to be only minor at best, not robust to plausible variations in the test design, and bi-directional rather than one-directional. We show to what extent the difference between Chen et al’s empirical findings and ours is due to the presence of time-averaged prices in the commodity index data that they use (price averaging induces spurious autocorrelation and predictability) and to features in their test procedures.
the latter are exogenous to the exchange rate dynamics. In our view, however, commodity prices are essentially financial asset prices that are set in a forward-looking way, exactly like exchange rates.
If both the exchange rate and the commodity prices are based on discounted future expectations, one should mostly observe contemporaneous correlations, not one-directional cross-predictability from one variable toward the other.
Using three different data sets and various econometric techniques, we do find the contemporaneous correlations as predicted by the financial asset view of commodity prices. Cross-predictability, in contrast, seems to be only minor at best, not robust to plausible variations in the test design, and bi-directional rather than one-directional. We show to what extent the difference between Chen et al’s empirical findings and ours is due to the presence of time-averaged prices in the commodity index data that they use (price averaging induces spurious autocorrelation and predictability) and to features in their test procedures.
Original language | Danish |
---|---|
Title of host publication | 22nd Annual Symposium, Society for Nonlinear Dynamics and Econometrics, CUNY, New York |
Publication date | 12 Apr 2014 |
Publication status | Published - 12 Apr 2014 |