Question 5: If there were a bias between repeated observations by the same observer, what would this tell us?
The repeated measurements would not be true replicates, because something would have changed in a systematic way between observations. This could be because the subjects had changed, perhaps as a result of practice at a test. This could not happen here, because the same image was measured twice. The observer may have changed, perhaps by changing their criterion for measurement. For whatever reasons the bias had arose, we could not use these observations to estimate the repeatability of the measurement.
Back to question.
To Martin Bland's home page.
This page maintained by Martin Bland.
Last updated: 26 April 2007.
Back to top.