Frequently asked questions on the design and analysis of measurement studies

I am often asked questions about studies of measurement error and of the agreement between different methods of measurement. I hope that this list will prove helpful. I expect the list to expand rapidly.

Is there a method I can use to assess the differences in limits of agreement between groups?
Interpreting the limits of agreement: do I have good or bad agreement?
Is there an acceptable value for the limits of agreement or the repeatability?
How do I estimate limits of agreement when the mean or SD of differences is not constant?
What is the origin of the formula for repeatablity?
Should all my observations lie between the limits of agreement?
How do I analyse observer variation studies?
How do I measure observer agreement when only positive observations are recorded?
What is the standard error of the within-subject standard deviation, s_w?
How should I calculate a within-subject coefficient of variation?
How can I decide the sample size for a study of the agreement between two methods of measurement?
How can I decide the sample size for a repeatability study?
How do I compare methods of measurement which give results in different units?
When one method of measurement is a gold standard, does the limits of agreement approach still work?
Why is plotting difference against standard method misleading?
How can I compare repeatability in matched samples?

How does pooling blood samples affect standard deviation?

Back to measurement studies menu

Back to Martin Bland's Home Page.

This page maintained by Martin Bland.
Last updated: 17 June, 2015.