Big news in small samples
1997-08-16
Research Paper
This publication is part of collection
| Related Files |
|---|
View PDF Version
(BigNews_1997.pdf, 0.3MB) |
Univariate time series regressions of the forex return on the forward premium generate mostly negative slope coefficients. Simple and refined panel estimation techniques yield slope estimates that are much closer to unity. We explain the two apparently opposing results by allowing for both additive and multiplicative news. No arbitrage arguments imply that the multiplicative news component must be identical across all exchange rates at a given point in time. Cross section estimates reveal that the movements in the multiplicative news component are so large that a negative slope coefficient for the post Bretton Woods time series regressions is not inprobable.
Keywords
Automatically Extracted Terms
- slope
- estimate
- currency
- premium
- exchange
- series
- model
- coefficient
- risk premium
- exchange rates
- assumption
- numeraire
- return
- variation
- intercept
- effect
- factor
- time variation
- hypothesis
- fisher hypothesis
