What is it about?
Shows that shrinkage of results is a simple consequence of random variation.
Featured Image
Why is it important?
Provides a simple demonstration of the fact that just because forward unbiasedness applies (whereby a statistic is on average equal to the parameter) does not mean that backward unbiasedness applies (whereby a parameter is on average equal to the statistic).
Read the Original
This page is a summary of: Transposed Conditionals, Shrinkage, and Direct and Indirect Unbiasedness, Epidemiology, September 2008, Wolters Kluwer Health,
DOI: 10.1097/ede.0b013e318181b3e3.
You can read the full text:
Resources
Contributors
The following have contributed to this page