“On the study of penalized LAD methods"
Penalized regression has been widely used in high-dimensional data analysis. Much recent work has been done on the study of penalized least squares methods. In this talk, I will focus on the study of penalized least absolute deviation (LAD) methods in high-dimensional settings. Some theoretical properties of the Lasso and the Adaptive Lasso are generalized to the LAD-Lasso and the LAD-Adaptive Lasso. The finite sample performance of proposed methods is demonstrated by simulation studies, and statistical applications in genetics are discussed.
Xiaoli Gao is an Assistant Professor of Statistics in the Department of Mathematics and Statistics at Oakland University. Her current main research interest is in high-dimensional data analysis and its statistical application in genetics.
Ellen Barnes giving Xianli Gao a Certificate of Appreciation from the Detroit Chapter