This paper develops vector autoregressive and Bayesian vector autoregressive models to
forecast the Indian Re/US dollar exchange rate which is governed by a managed floating
exchange rate regime. It considers extensions of the monetary model that include the
forward premium, capital inflows, volatility of capital flows, order flows and central bank
intervention. The study finds that the monetary model generally outperforms the naïve
model. It also finds that forecast accuracy can be improved by extending the monetary
model to include forward premium, volatility of capital inflows and order flow.
Information on intervention by the central bank also helps to improve forecasts at the
longer end. The study also reports that the Bayesian vector autoregressive models generally
outperform their corresponding VAR variants.