Activity Number:
|
67
- Section on Statistical Computing: Data Science
|
Type:
|
Contributed
|
Date/Time:
|
Monday, August 3, 2020 : 10:00 AM to 2:00 PM
|
Sponsor:
|
Section on Statistical Computing
|
Abstract #311046
|
|
Title:
|
The Modified Directed Likelihood in High-Dimensions
|
Author(s):
|
Yanbo Tang* and Nancy Reid
|
Companies:
|
University of Toronto and University of Toronto
|
Keywords:
|
Higher-Order Asymptotics;
Nuisance Parameters ;
Profile Likelihood ;
Asymptotic Methods
|
Abstract:
|
We examine the r* approximation to the significance function with increasing numbers of nuisance parameters. We establish the relative influence of the nuisance parameter correction and show that it is larger than the correction for non-normality, when the parameter dimension p is increasing with the number of observations, and establish the rates. We specialize the results to linear exponential families and location-scale families. We illustrate the results with simulations, and link to related work by Sartori (2003) and Shun and McCullagh (1995).
|
Authors who are presenting talks have a * after their name.