2. Methodological aspects

View

5. Errors in measurement

There are two main types of error that affect epidemiologic studies, systematic error and random error. Epidemiologists try to reduce both types of error in the design of a study.


Systematic errors are associated with a flaw in the design of a study or of an instrument used for measurement. Suppose you were using a stopwatch to measure the times for runners in a 100-metre event but the stopwatch you were using was running slow. The times for all the runners that you measured would be incorrect and would underestimate the actual time. This is an example of systematic error, also called bias.

Random errors in the time measurement could occur by holding the stopwatch differently, differences in your reaction time in pressing the stop button, or how you read the time on the watch. Some of these errors will lead to a reading that is too high or too low but on average the readings would not tend to be too high or too low. The effect of these errors would become less