学习了

学习了

就是一种提高估计效率的的估计量，
有兴趣的坛友可以参考如下两篇文章：
Regression, Prediction and Shrinkage
Regression Shrinkage and Selection via the Lasso Regression Shrinkage and Selection via the Lasso

Shrinkage estimator are weighted averages of historical data and some other estimate, where the weights and other estimates are defined by the analyst. Shrinkage estimators reduce(shrink) the influence of historical outliers through the weighting process. The mean return and covariance are the parameters most often adjusted with shrinkage estimators. This tool is most useful when the data set is too small that historical values are not reliable estimates of future parameters.

学习了~~~~~