Handbook of Exchange Rates

9.2 Panel Data Exchange Rate Determination Studies

In a data set of N countries indexed by and T time-series observations indexed by , let x_it be a (scalar) prediction variable for s_{i, t+k}, the log-exchange rate for country i. Mark and Sul (2001) and Cerra and Saxena (2010) investigate the empirical link between the monetary model fundamentals and the exchange rate. They set x_{i, t} to be the deviation of today's exchange rate s_{i, t} from the long-run equilibrium value predicted by economic theory. In the case of the monetary model, x_{i, t} = f_{i, t} − s_{i, t}, where f_{i, t} = (m_{i, t} − m_{0, t}) − λ(y_{i, t} − y_{0, t}), country “0” is the base country, m is the log-money stock, and y is log-real income. They used the panel exchange rate predictive regression

where η_{i, t+k} = γ_i + θ_t+k + ϵ_{i, t+k} has an error-component representation with individual (fixed) effect γ_i, common time effect θ_t, and idiosyncratic effect ϵ_{i, t+k}. Rapach and Wohar (2004) reject the null hypothesis of slope coefficient homogeneity at the one-percent level using Mark and Sul's data set.

Groen (2005) uses a four-country panel and pools a vector error-correction model (VECM). Letting X_{i, t} = (s_{i, t}, (m_{i, t} − m_{0, t}), (y_{i, t} − y_{0, ...}