Measurement Errors

About measurement errors

Mention must also be made of measurement errors. Measurement system errors can be divided into two categories, systematic and random errors. Various mechanisms exist for reducing these two types of error.

A characteristic feature of all systematic errors is that they produce errors which are consistently on the same side of the true value, i.e. either all the errors are positive or they are all negative. Systematic errors arise from many causes. These include system disturbance due to measurement, environmental changes (modifying inputs) and drift in instrument characteristics. Large errors due to instrument characteristic drift are avoided by recalibrating instruments at suitable intervals. In the case of other sources of systematic error, a good measurement technician can largely eliminate errors by calculating their effect and correcting the measurements. This is done automatically by using intelligent instruments.

Random errors are in many ways easier to deal with because they consist generally of small perturbations of the measurement either side of the correct value, i.e. positive errors and negative errors occur in approximately equal numbers for a series of measurements made of the same quantity. Therefore, random errors can be largely eliminated by averaging a few measurements of the same quantity. Unfortunately, averaging a number of measurements cannot be guaranteed to produce a value close to the true one because random errors occasionally cause large perturbations from the true value. Thus, it is necessary to describe measurements subject to random errors in probabilistic terms, typically that there is a 95% probability that the measurement error is within boundaries of ± 1% from the true value.

Back to Principles of Measurement