Introduction to Epidemiology 6th Edition by Ray M Merrill

Exercise 3

Screening has been associated with certain types of measurement bias. Match the descriptions of bias resulting fromscreening in the left column with the names of these types of bias in the right column.

___ The screening test looks better than it actually is, because younger, healthier people are more likely to get the test.	A. Lead-time bias
___ Screening identifies an illness that would not have shown clinical signs before death fromother causes.	B. Length bias
___ Slow-progressing cases of disease with a better prognosis are more likely to be identified than faster-progressing cases of disease with a poorer prognosis. Thus, cases diagnosed through screening tend to have a better prognosis than the average of all cases.	C. Selection bias
___ Difference in the time between the date of diagnosis with screening and the date of diagnosis without screening, which, if counted in the survival time of patients, will give a misleading picture of the benefits of treatment.	D. Overdiagnosis bias

Step 1 of 7

Selection bias is one type of bias that occurs when the choice is nonrandom and non-representative for formulation of the screen test data. In terms of survival, it can make a test look better or worse than it actually is.

For example, if the screening facility were distantly located, younger people would appear for the screening than older ones. Thus, a little proportion of the people would develop the illness in the screening population and the test would look better.

Hence, the screening test that looks better than it actually is can be matched with.