Answers are grounded in this paper and cite their sources.
This paper finds that many of the anomalies in the exchange rate literature can be explained in large measure by recurrent shifts in the co-integrating vector. We find that the co-integrating vector implied by a composite monetary model experiences parameter shifts on five occasions over the modern period of floating. Within the implied regimes of relative parameter constancy we find that parameter estimates are mostly significant and of the correct sign. We also find co-integration and considerable improvement in the out-of-sample fit on the part of all the structural models examined.
No takes yet. Share an insight, caveat, or question.
Goldberg et al. (1996) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: