Conventional tests of the predictability of stock returns could be invalid, that is reject the null too frequently, when the predictor variable is persistent and its innovations are highly correlated with returns. We develop a pretest to determine whether the conventional t-test leads to invalid inference and an efficient test of predictability that corrects this problem. Although the conventional t-test is invalid for the dividend–price and smoothed earnings–price ratios, our test finds evidence for predictability. We also find evidence for predictability with the short rate and the long-short yield spread, for which the conventional t-test leads to valid inference.

In this paper we focus on the assumption of a common efficient frontier when performing an efficiency study for the banking sector. The fact that environmental factors that are not appropriately controlled may easily bias efficiency estimates. First, we estimate a common cost and profit frontier. In this first stage, as an innovation to the literature, we use exogenously computed input prices rather than the normally used endogenous input prices. Second, we regress the estimated inefficiencies on a set of a bank’s strategic choices, local banking market variables, and local (regional) macro variables. For the analysis, we use a unique dataset of 401 largely independent cooperative local banks in the Netherlands for the years 1998 and 1999. Our results show that the use of exogenous input prices rather than endogenous input prices is particularly important for the cost frontier as the spread in cost inefficiencies becomes larger and more plausible. Our second stage results suggest that most of the estimated inefficiency indeed is managerial (X-) inefficiency. Environmental factors do play a role, but only to a limited extent.