|
Activity Number:
|
444
- Recent Advances in Statistical Methodology for Big Data
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Thursday, August 12, 2021 : 4:00 PM to 5:50 PM
|
|
Sponsor:
|
IMS
|
|
Abstract #318862
|
|
|
Title:
|
Some Results on Identifiable Parameters That Cannot Be Identified from Data, Including Constant Correlation Between Gaussian Observations
|
|
Author(s):
|
Christian Hennig*
|
|
Companies:
|
University of Bologna
|
|
Keywords:
|
identifiability;
correlation;
indistinguishability;
k-means clustering
|
|
Abstract:
|
I will show that some theoretically identifiable parameters cannot be identified from data, meaning that no consistent estimator of them can exist. Examples are a constant correlation between Gaussian observations (in presence of such correlation not even the mean can be identified from data), and cluster memberships in a fixed classification model underlying k-means clustering. I will define non-identifiability from data and indistinguishability from data. Two different constant correlations between Gaussian observations cannot even be distinguished from data.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2021 program
|
