The development of asset pricing models that rely on instrumental variables together with the increased availability of easily accessible economic time-series have renewed interest in predicting security returns. Evaluating the significance of these new research findings, however, is no easy task. Because these asset pricing theory tests are not independent, classical methods of assessing goodness-of-fit are inappropriate. This study investigates the distribution of the maximal R-square when k of m regressors are used to predict security returns. The authors provide a simple procedure that adjusts critical R-square values to account for selecting variables by searching among potential regressors.

We analyze a multi‐period model of trading with differentially informed traders, liquidity traders, and a market maker. Each informed trader's initial information is a noisy estimate of the long‐term value of the asset, and the different signals received by informed traders can have a variety of correlation structures. With this setup, informed traders not only compete with each other for trading profits, they also learn about other traders' signals from the observed order flow. Our work suggests that the initial correlation among the informed traders' signals has a significant effect on the informed traders' profits and the informativeness of prices.

We analyze a multi-period model of trading with differentially informed traders, liquidity traders, and a market maker. Each informed trader's initial information is a noisy estimate of the long-term value of the asset, and the different signals received by informed traders can have a variety of correlation structures. With this setup, informed traders not only compete with each other for trading profits, they also learn about other traders' signals from the observed order flow. Our work suggests that the initial correlation among the informed traders' signals has a significant effect on the informed traders' profits and the informativeness of prices.

Patterns in stock market trading volume, trading costs, and return volatility are examined using New York Stock Exchange data from 1988. Intraday test results indicate that, for actively traded firms trading volume, adverse selection costs, and return volatility are higher in the first half‐hour of the day. This evidence is inconsistent with the Admati and Pfleiderer (1988) model which predicts that trading costs are low when volume and return volatility are high. Interday test results show that, for actively traded firms, trading volume is low and adverse selection costs are high on Monday, which is consistent with the predictions of the Foster and Viswanathan (1990) model.

Using a unique database of daily transactions from Australian equity managers, we investigate the relation between institutional trading and share returns. The 34 institutional investors included in our sample exhibit a statistically and economically significant ability to predict large capitalization share returns for the ten days following their trades. Detailed analysis indicates that investment manager style is important in understanding the link between institutional trading and stock returns. The contemporaneous relation between institutional trading and returns depends on trade size, broker use, and investment style. We find growth-oriented managers are momentum traders, while style-neutral and value managers are contrarian.

The development of asset pricing models that rely on instrumental variables together with the increased availability of easily‐accessible economic time‐series have renewed interest in predicting security returns. Evaluating the significance of these new research findings, however, is no easy task. Because these asset pricing theory tests are not independent, classical methods of assessing goodness‐of‐fit are inappropriate. This study investigates the distribution of the maximal when k of m regressors are used to predict security returns. We provide a simple procedure that adjusts critical values to account for selecting variables by searching among potential regressors.

The development of asset pricing models that rely on instrumental variables together with the increased availability of easily-accessible economic time-series have renewed interest in predicting security returns. Evaluating the significance of these new research findings, however, is no easy task. Because these asset pricing theory tests are not independent, classical methods of assessing goodness-of-fit are inappropriate. This study investigates the distribution of the maximal R2 when k of m regressors are used to predict security returns. We provide a simple procedure that adjusts critical R2 values to account for selecting variables by searching among potential regressors.