Prediction of Graduate Performance in Economics

Professor Hansen's paper describes an effort to predict the success of graduate students in economics at The University of Wisconsin. Undergraduate grade point average, GRE scores, and the quality of the undergraduate schools were used as independent variables in a linear multiple regression model. Graduate grade point average was the dependent variable. The value of the independent variables as predictors is analyzed both jointly and in isolation. Among the important conclusions reached by Hansen is that heavy reliance upon a single predictor such as the undergraduate grade point average is unwise, that the GRE quantitative score takes on greater significance as the graduate student advances into the second year of his program, and that school quality must be taken into account.     

游戏变革者

在撰写汉森电子汽车报告的时候，我经常与世界各地的专家讨论某些能在很长一段时期影响汽车电子产品的趋势和技术。我花费了很长的时间去思考未来——新技术是否有一天能够成为游戏的变革者，或者是否一个经过论证后确立的行业标准能够真正降低成本。而实际上，汉森报告每年一次的重点论证和评价的新技术，最终都被广泛应用在汽车上。     

Averaging estimators for autoregressions with a near unit root

This paper uses local-to-unity theory to evaluate the asymptotic mean-squared error (AMSE) and forecast expected squared error from least-squares estimation of an autoregressive model with a root close to unity. We investigate unconstrained estimation, estimation imposing the unit root constraint, pre-test estimation, model selection estimation, and model average estimation. We find that the asymptotic risk depends only on the local-to-unity parameter, facilitating simple graphical comparisons. Our results strongly caution against pre-testing. Strong evidence supports averaging based on Mallows weights. In particular, our Mallows averaging method has uniformly and substantially smaller risk than the conventional unconstrained estimator, and this holds for autoregressive roots far from unity. Our averaging estimator is a new approach to forecast combination.     

Time series econometrics for the 21st century

What topics should be taught to undergraduate students in econometric time series?     

Uncertainty and the partial loss offset provision

Sufficient conditions are given for a tightening of the partial loss offset provision to reduce, respectively to stimulate, individual risk-taking.     

A note on first degree stochastic dominance

A link is established between stochastic dominance and a different dominance relationship which we call pointwise dominance. This provides the basis for making several comparisons of expected values of non-decreasing functions of random variables. We discuss economic problems for which the application of stochastic dominance results depends on this link.     

A Bayesian operationalization of the resource‐based view

This paper argues that the gap between the theoretical utility and the practical utility of the resource‐based view (RBV) may be narrowed by operationalizing the theory more consistently with Penrose's original framework. The operationalization proposed here is a twofold approach. First, the RBV may be enhanced by the explicit recognition of Penrose's two classes of resources, namely, administrative resources and productive resources. This distinction suggests a focus on the administrative decisions of managers that lead to economic performance. Second, we argue that the RBV is a theory about extraordinary performers or outliers—not averages. Therefore, the statistical methods used in applying the theory must account for individual firm differences, and not be based on means, which statistically neutralize firm differences. We propose a novel Bayesian hierarchical methodology to examine the relationship between administrative decisions and economic performance over time. We develop and explain a measure of competitive advantage that goes beyond comparisons of economic performance. This Bayesian methodology allows us to make meaningful probability statements about specific, individual firms and the effects of the administrative decisions examined in this study. Copyright © 2004 John Wiley & Sons, Ltd.     

Instrumental variables procedures for estimating linear rational expectations models

This paper illustrates how to use instrumental variables procedures to estimate the parameters of a linear rational expectations model. These procedures are appropriate when disturbances are serially correlated and the instrumental variables are not exogenous. We compare our procedures to some alternative estimators that estimate free parameters from restrictions implied by the Euler equations. The procedures are applicable to a variety of linear rational expectations models, several examples of which we cite.