This website is for students following the M.Sc. in Evidence Based Practice at the University of York.
Question 1: What does the regression line tell us about the agreement between capillary glucose and laboratory glucose?
The regression line tells us very little about the agreement. If there were perfect agreement with no measurement error the points would lie on the line of equality, y = 0 + 1.00x. In the presence of any error in the x variable the slope of the line is expected to be less than one and the intercept greater than zero. This happens in this example, but we cannot tell whether this is due to the expected bias in the regession coefficients or to a real deviation from agreement.
Back to question.
To Martin Bland's home page.
This page maintained by Martin Bland.
Last updated: 26 February, 2005.
Back to top.