JAMES FRANCIS HANNAN LECTURE SERIES Department of Statistics and Probability Michigan State University
暂无分享,去创建一个
We study the behavior of robust regression and least squares in the un-penalized case for 0 < p=n < 1. Surprisingly it turns out individual coecients are still asymptotically normal unbiased at rate 1= p n but the variance diers from the xed p situation with important implications
[1] D. Freedman,et al. Asymptotics of Graphical Projection Pursuit , 1984 .
[2] Peter J. Bickel,et al. Measuring reproducibility of high-throughput experiments , 2011, 1110.4705.
[3] John W. Tukey,et al. A Projection Pursuit Algorithm for Exploratory Data Analysis , 1974, IEEE Transactions on Computers.
[4] Nancy R. Zhang,et al. Subsampling methods for genomic inference , 2010, 1101.0947.