The Myth of Long-Horizon Predictability

By Jacob Boudoukh, Matthew P. Richardson, Robert F. Whitelaw. 2005

308 citations recorded by the source corpus.

The prevailing view in finance is that the evidence for long-horizon stock return predictability is significantly stronger than that for short horizons. We show that for persistent regressors, a characteristic of most of the predictive variables used in the literature, the estimators are almost perfectly correlated across horizons under the null hypothesis of no predictability. For example, for the persistence levels of dividend yields, the analytical correlation is 99% between the 1- and 2-year horizon estimators and 94% between the 1- and 5-year horizons, due to the combined effects of overlapping returns and the persistence of the predictive variable. Common sampling error across equations leads to ordinary least squares coefficient estimates and R2s that are roughly proportional to the horizon under the null hypothesis. This is the precise pattern found in the data. The asymptotic theory is corroborated, and the analysis extended by extensive simulation evidence. We perform joint tests across horizons for a variety of explanatory variables, and provide an alternative view of the existing evidence.

Subfields: Economics and Econometrics, Finance

View Paper: https://www.semanticscholar.org/paper/cc49c8c7cc42847a61e823961e34369c49bac702

Citations in the corpus

• Predictability of Returns and Cash Flows (2011, unknown): “However, Boudoukh et al. (2008) argue that longhorizon and short-horizon predictability estimators are highly correlated, presenting little independent information on the presence of return predictability.”
• Time-varying short-horizon predictability ☆ (2008, unknown): “As in Campbell and Shiller (1988), we construct the dividend yield, DY, using the sum of dividends on the CRSP value-weighted market portfolio smoothed over the past 12 months and scaled by the price level of the index.”
• Natural Expectations, Macroeconomic Dynamics, and Asset Pricing (2012, unknown): “The wide confi dence intervals for (2) and (4) may seem surprising; they are due to the high persistence of the P/E10 and the use of overlapping data for consumption growth and excess returns (see Boudoukh, Richardson, and Whiltelaw 2008).”
• The Evolution of Stock Market Efficiency Over Time: A Survey of the Empirical Literature (2011, unknown): “…variables such as the dividend–price ratio, earnings–price ratio, book-to-market ratio and various measures of the interest rates (recent studies include Boudoukh et al., 2008; Campbell and Thompson, 2008; Cochrane, 2008; Lettau and Nieuwerburgh, 2008; Welch and Goyal, 2008; Hjalmarsson, 2009).”
• Predicting market returns using aggregate implied cost of capital (2013, unknown): “…Myers, and Swaminathan (1999), Goyal and Welch (2003), Lewellen (2004), Ang and Bekaert (2007), Boudoukh, Michaely, Richardson, and Roberts (2007), Boudoukh, Richardson, and Whitelaw (2008), Cochrane (2008), Lettau and Nieuwerburgh (2008), Rytchkov (2008), Brennan and Taylor (2010), and Kelly and…”
• Expected stock returns and variance risk premia (2007, unknown): “, Boudoukh et al. (2008) and Goyal and Welch (2003, 2008).”
• Forecasting Stock Market Returns: The Sum of the Parts is More than the Whole (2011, unknown): “We use non-overlapping returns to avoid the concerns with the measurement of R-squares with overlapping returns pointed out by Valkanov (2003) and Boudoukh, Richardson, and Whitelaw (2008).”
• Technological Innovations and Aggregate Risk Premiums (2009, unknown): “13 In addition to patent shocks and R&D shocks, I include the following predictive variables in tests: Lagged market returns and premiums (Fama and French, 1988a), the dividend-price ratio “d − p” (Shiller, 1984; Campbell and Shiller, 1988; Fama and French, 1988b), the term spread “Term” and the def”
• Multifactor models and their consistency with the ICAPM (2012, unknown): “…(1999), Kilian (1999), Valkanov (2003), Lewellen (2004), Torous, Valkanov, and Yan (2004), Campbell and Yogo (2006), Ang and Bekaert (2007), and Boudoukh, Richardson, and Whitelaw (2008). coefficients associated with TERM and CL, which now become negative, although the slope for CL is highly…”
• Stock Return Predictability and Variance Risk Premia: Statistical Inference and International Evidence (2011, unknown): “Boudoukh, Richardson, and Whitelaw (2008), for instance, have recently shown that even in the absence of any increase in true predictability, the values of the R2s in regressions involving highly persistent predictor variables and overlapping returns, by construction, will increase roughly…”
• Can investor sentiment be a momentum time-series predictor? Evidence from China (2017, unknown): “See Boudoukh et al. (2008) for the caveats in long-horizon regressions.”