Statistical inference and estimation in high-dimensional data
Conference
Category: International Statistical Institute
Proposal Description
High-dimensional data often pose challenges due to the curse of dimensionality, multicollinearity, and overfitting. Regularization methods such as LASSO, SCAD, and Elastic Net provide effective solutions to these issues. This session will explore recent advancements in estimation using regularized techniques for various statistical models. Particularly, our session will include robust regression, robust estimation for response theory model, and small area estimation. We anticipate that this session will offer a valuable opportunity for researchers to exchange ideas and discuss recent developments in high-dimensional data analysis.
Submissions
- A forward sparse sufficient dimension reduction in binary classification via penalized gradient learning
- Bayesian Elastic Net and Fused Lasso Modeling in Small Area Estimation
- Penalized maximum likelihood estimation with nonparametric Gaussian scale mixture errors
- l0-Regularized Item Response Theory Model for Robust Ideal Point Estimation