|
Activity Number:
|
468
- Statistical Challenges and Novel Methodologies for Analyzing Health Outcomes
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Wednesday, August 10, 2022 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Nonparametric Statistics
|
|
Abstract #323572
|
|
|
Title:
|
Analysis of Large Data with Subsampling
|
|
Author(s):
|
Zhezhen Jin* and Yujing Yao
|
|
Companies:
|
Columbia University and Columbia University
|
|
Keywords:
|
large data;
subsampling;
perturbation
|
|
Abstract:
|
Analysis of large data is challenging due to its size and computational issues. Subsampling methods and divide-and-conquer procedures are appealing because they ease computational burden. However, it is challenging to preserve the validity of the resulting estimation and inference. In this talk, we will discuss a perturbation subsampling approach based on independent and identically distributed stochastic weights for the analysis of large data. We justify the method based on optimizing convex objective functions by establishing asymptotic consistency and normality for the resulting estimators. Simulation studies and real data analysis will also be used to illustrate the finite sample performance of the method.
|
Authors who are presenting talks have a * after their name.
