What is the difference between adaptive and classical testing?

Answer 1

In classical testing the view that an individual's observed score on a test is the sum of a true score component for the participant, plus an independent measurement error component. A few simple premises about these components lead to important relationships among validity, reliability, and other test score statistics whereas adaptive testing is a sequential form of individual testing in which successive items in the test are chosen based primarily on the psychometric properties and content of the items and the participant's response to previous items.



Classical Test Theory - The earliest theory of measurement that attempts to estimate the strength of the relationship between the observed score and the true score. The mathematic expression is: X = T + E, where X is the observed score, T is the true score and E is the error; also known as classical reliability theory.

Reliability estimation is achieved through Pearson's correlation between the observed and true score, and is known as the reliability index. A high value for Pearson's r indicates high reliability. Two assumptions are important for reliability estimation. The first is the assumption of independence, which states that the true score is unrelated to, or independent of, the error score. This assumption allows estimation of the square of the reliability index (ratio of true variance to observed variance) through parallel testing. This leads to the parallel tests assumption: for two tests designed to test the same construct on the same subjects, the T remains the same. Specifically, scores on both tests have the same variance; and the errors on both tests are mutually independent. Read the METRIC Primer for more information.


Computer Adaptive Testing (CAT) - A computer-administered questionnaire based on the item response theory (IRT). The examinee responds to a sequence of questions, selected from an item pool. A program calculates statistics after each response and determines the subsequent order of items based on the examinee’s responses to the previous items. It attempts to determine the examinee’s true ability.