论文部分内容阅读
We propose a Random Splitting Model Averaging procedure,RSMA,to achieve stable predictions in high-dimensional linear models.
Stable Prediction in High-Dimensional Linear Models
【摘 要】
：
We propose a Random Splitting Model Averaging procedure,RSMA,to achieve stable predictions in high-dimensional linear models.
【机 构】
：
Institute of Statistical Sciences,College of Mathematics and Statistics,Shenzhen University,Shenzhen
【出 处】
：
上海交通大学
【发表日期】
：
2016年4期
其他文献
Identifying dominating genes for drug targets must both consider biologically mean-ingful outcomes and employ an ensemble of e ective data analytics for the identi cation.
For complete ultrahigh-dimensional data,sure independent screening methods can effectively reduce the dimensionality while ensuring that all the active variables can be retained with high probability.
The talk will cover two extensions of the sufficient dimensional reduction method.In one project,we develop a semiparametric functional single index model to study the relation between a univariate re
The main challenge in the context of cure rate analysis is that one never knows whether censored subjects are cured or uncured,or whether they are susceptible or insusceptible to the event of interest
This research is aimed at analyzing factors affecting the survival of dengue fever(DF)patients in Muhammadiyah Medan Hospital.
Distributed detection fusion with high-dimension conditionally dependent observations is known to be a challenging problem.
Prediction precision is arguably the most relevant criterion of a model in practice and is often a sought after property.
In this paper,we introduce a nonparametric test against the constancy of the factor loading matrix of large dimensional continuous time factor model using high frequency data.
A screening problem is tackled by proposing a parametric class of distributions designed to match the behavior of the partially observed screened data.