Abstract Using real-time data, we show that currency excess return predictability is in part due to mispricing. First, the risk-adjusted profitability of systematic trading strategies decreases after dissemination of the underlying academic research, suggesting that market participants learn about mispricing from publications. Moreover, the decline is greater for strategies with larger in-sample profits and lower arbitrage costs. Second, the effect of comprehensive risk adjustments on trading profits is limited, and signal ranks and alphas decay quickly. The finding that analysts’ forecasts are inconsistent with currency predictors implies that investors’ trading contributes to mispricing and suggests biased expectations as a possible explanation.

Methods are described for the appropriate use of data obtained and analysed in real time to represent the output gap. The methods employ cointegrating VAR techniques to model real-time measures and realizations of output series jointly. The model is used to mitigate the impact of data revisions; to generate appropriate forecasts that can deliver economically meaningful output trends and that can take into account the end-of-sample problems encountered in measuring these trends; and to calculate probability forecasts that convey in a clear way the uncertainties associated with the gap measures. The methods are applied to data for the United States 1965q4–2004q4, and the improvements over standard methods are illustrated.