Forecasting Long-Term Equity Returns: A Comparison of Popular Methodologies

Abstract

Many investors need to make long-term asset class forecasts for planning and portfolio construction purposes. We examine the empirical performance of two different approaches to forecasting future ten-year equity returns: a regression methodology using CAPE and a more traditional “building block” approach. The regression approach produces estimates that are poor predictors of subsequent actual returns. The “building block” approach (BBA) outperforms the regression methodology (in terms of root mean squared error) with the repricing component helping to capture periods of poor equity returns. A high CAPE value is not necessarily cause for alarm and changes in asset allocation. If an investor plans to use a methodology that over time will prove more accurate, then the historical record is more supportive of the BBA approach, with or without a repricing component based on current P/E.