More on bias and reliability. The previous exercise gives 5 true values for lengths. A subject measures each length twice by eye. Make up a set of results from this activity that matches each of the descriptions below.

For simplicity, assume that bias means the same fixed error every time rather than an “on the average” error in many measurements.

(a) The subject has a bias of 0.5 inch too long and is perfectly reliable.

(b) The subject has no bias but is not perfectly reliable, so that the average difference in repeated measurements is 0.5 inch.

AppendixLO1