Forecasting Output with the Composite Leading Index: A Real-Time Analysis

Abstract We examine the ability of the composite index of leading economic indicators to predict future movements in aggregate economic activity. Previous examinations of predictive performance have evaluated either the in-sample residual errors from a forecasting equation fitted to the entire sample of data or the out-of-sample forecast errors from an equation fitted to a subsample of the data. Unlike previous evaluations, we perform a real-time analysis, which uses the provisional and partially revised data for the leading index that were actually available historically, along with recursive out-of-sample forecasts. We find a substantial deterioration of forecasting performance in the real-time framework. Key Words: CausalityEvaluationPrediction