Activity Number:
|
69
- Modern Statistical Methods for Multi-Scale and Time Series Data
|
Type:
|
Contributed
|
Date/Time:
|
Sunday, July 30, 2017 : 4:00 PM to 5:50 PM
|
Sponsor:
|
International Indian Statistical Association
|
Abstract #323881
|
|
Title:
|
Approximate Sufficient Dimension Reduction: a Multiresolution Analysis
|
Author(s):
|
Siamak Noorbaloochi* and David Nelson
|
Companies:
|
VA Health Care System and Dept Veterans Affairs, Univ Minnesota
|
Keywords:
|
Sufficient Summary ;
Multiresolution Analysis ;
Density Ratio ;
Spectral decomposition
|
Abstract:
|
Analysis of Variance of density ratios is used to construct X-sufficient and approximate X-sufficient summaries. However, when density ratios are hard to specify, a multiresolution analysis is used for approximating X-sufficient summaries via sequentially projecting into inverse-regression conditional density ratio subspaces. Mercer's spectral decomposition theorem and the corresponding functional principal components provide the local approximating subspaces.
|
Authors who are presenting talks have a * after their name.