The myth of long-horizon predictability

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 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- ear horizons. Common sampling error across equations leads to ordinary least squares coefficient estimates and R(2)s that are roughly proportional to the horizon under the null hypothesis. This is the precise pattern found in the data. We perform joint tests across horizons for a variety of explanatory variables and provide an alternative view of the existing evidence.