|
Activity Number:
|
522
- Life Science Applications of Data Science
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Thursday, August 11, 2022 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Statistical Learning and Data Science
|
|
Abstract #322202
|
|
|
Title:
|
Significance Tests Based on Sieve Quasi-Likelihood Ratio Test Using Neural Networks with Application to Genetic Association Studies
|
|
Author(s):
|
Xiaoxi Shen* and Chang Jiang and LYUDMILA SAKHANENKO and Qing Lu
|
|
Companies:
|
Texas State University and University of Florida and Michigan State University and University of Florida
|
|
Keywords:
|
Sieve quasi-likelihood ratio test;
nonparametric least squares
|
|
Abstract:
|
Despite the great success of applications of neural networks in many different fields, such as natural language processing and image recognition, lack of research focuses on the interpretation of neural network models. In this paper, we propose a sieve quasi-likelihood ratio test based on neural networks with one hidden layer to conduct significance tests of input features. The test statistic has asymptotic chi-squared distribution so that it is easy to apply in real data analysis. The validity of the asymptotic distribution is investigated via simulation and we applied our proposed test to perform genetic association analysis on the sequencing data from Alzheimer's Disease Neuroimaging Initiative (ADNI).
|
Authors who are presenting talks have a * after their name.
