tay's as good as cay: Reply

In a recent comment on our published work [Lettau, M., Ludvigson, S., 2001. Consumption, aggregate wealth, and expected stock returns. Journal of Finance 56, 815-850], Michael Brennan and Yihong Xia [2005. tay's as good as cay. Finance Research Letters 2, 1-14] advance the following argument: A “mechanistic” variable tay, where t is a linear time trend, forecasts stock returns. Since “t has no foresight,” the argument goes, the predictive power of this variable must be attributable to what they call “look-ahead bias.” The authors assert that cay is subject to the same look-ahead bias (generated because we use the full sample to estimate the cointegrating parameters in cay), implying that its forecasting power must be spurious. In this response, we explain why this critique is misplaced.