The out-of-sample R^(2) is designed to measure forecasting performance without look-ahead bias.However,researchers can hack this performance metric even without multiple tests by constructing a prediction model using ...The out-of-sample R^(2) is designed to measure forecasting performance without look-ahead bias.However,researchers can hack this performance metric even without multiple tests by constructing a prediction model using the intuition derived from empirical properties that appear only in the test sample.Using ensemble machine learning techniques,we create a virtual environment that prevents researchers from peeking into the intuition in advance when performing out-of-sample prediction simulations.We apply this approach to robust monitoring,exploiting a dynamic shrink-age effect by switching between a proposed forecast and a benchmark.Considering stock return forecasting as an example,we show that the resulting robust monitoring forecast improves the average performance of the proposed forecast by 15%(in terms of mean-squared-error)and reduces the variance of its relative performance by 46%while avoiding the out-of-sample R^(2)-hacking problem.Our approach,as a final touch,can further enhance the performance and stability of forecasts from any models and methods.展开更多
We examine the relationships with firm performance of the internal pay gap among individual members of the top management team(TMT) and the compensation level of TMT members relative to their industry peers. We find t...We examine the relationships with firm performance of the internal pay gap among individual members of the top management team(TMT) and the compensation level of TMT members relative to their industry peers. We find that pay gap is positively related to firm performance and that this positive relation is stronger when the TMT pay level is higher than the industry median. However, we do not observe such effects in Chinese state-owned enterprises(SOEs),in which both the executive managerial market and compensation are government-regulated. We also document that cutting central SOE managers' pay level can increase firm value, whereas doing so for local SOE managers has the opposite effect. Our findings have important implications for research on TMT compensation as well as for policy makers considering SOE compensation reform.展开更多
文摘The out-of-sample R^(2) is designed to measure forecasting performance without look-ahead bias.However,researchers can hack this performance metric even without multiple tests by constructing a prediction model using the intuition derived from empirical properties that appear only in the test sample.Using ensemble machine learning techniques,we create a virtual environment that prevents researchers from peeking into the intuition in advance when performing out-of-sample prediction simulations.We apply this approach to robust monitoring,exploiting a dynamic shrink-age effect by switching between a proposed forecast and a benchmark.Considering stock return forecasting as an example,we show that the resulting robust monitoring forecast improves the average performance of the proposed forecast by 15%(in terms of mean-squared-error)and reduces the variance of its relative performance by 46%while avoiding the out-of-sample R^(2)-hacking problem.Our approach,as a final touch,can further enhance the performance and stability of forecasts from any models and methods.
基金support of the National Natural Science Foundation of China (71372150, 71572197, and 71032006)
文摘We examine the relationships with firm performance of the internal pay gap among individual members of the top management team(TMT) and the compensation level of TMT members relative to their industry peers. We find that pay gap is positively related to firm performance and that this positive relation is stronger when the TMT pay level is higher than the industry median. However, we do not observe such effects in Chinese state-owned enterprises(SOEs),in which both the executive managerial market and compensation are government-regulated. We also document that cutting central SOE managers' pay level can increase firm value, whereas doing so for local SOE managers has the opposite effect. Our findings have important implications for research on TMT compensation as well as for policy makers considering SOE compensation reform.
