In an earlier Word Play post, we discussed one of the cornerstones of psychometrics: Validity, the extent to which a measurement tool, like an examination, measures what it is intended to measure.

Another important aspect of psychometrics is Reliability. Reliability refers to the overall sustained consistency of a measurement given similar candidates and conditions. Certification examination scores are considered highly reliable if they are reproducible and consistent from one test administration to another. In other words, if a group of test takers with similar characteristics were given the same exam, essentially the same results would be obtained.

After each examination is administered, PTC calculates a reliability coefficient for that examination. The reliability coefficient can range from 0.0 (highly unreliable) to 1.0 (highly reliable). Thanks to the consistent way in which we develop and administer our client examinations, most of our client reliability coefficients typically fall in the range of .90 to 1.0 — which means that the examinations developed by PTC demonstrate a high level of reliability.

Although Validity and Reliability are distinct measurement characteristics, both are very important to the development of a psychometrically sound examination.