What is it about?

Medical screening is based on measurements on a continuous scale. They have to be discretised to positives and negatives, separated by a threshold. The article deals with setting this threshold so as to balance the two kinds of errors that are committed (false negatives and false positives). The novelty of the method is that it takes into account the consequences of these errors, not only their probabilities.

Featured Image

Perspectives

Statistics is a profession and science of making decisions in the presence of uncertainty with limited resources. This can be interpreted as management of error in statistical inference. Statistics should reflect how we deal with such problems in our everyday lives --- we consider both (conditional) probabilities and the gravity (ramifications) of the errors. Ignore the latter at your peril. The limitation on resources raise the profile of study design.

Dr Nicholas T Longford
SNTL

Read the Original

This page is a summary of: Screening as an application of decision theory, Statistics in Medicine, August 2012, Wiley,
DOI: 10.1002/sim.5554.
You can read the full text:

Read

Contributors

The following have contributed to this page