Test-retest with Equivalent Forms |
with the second administration perhaps coming a week after the first. The obtained correlation coefficient would indicate the stability of the scores.If you wanted to evaluate the reliability of a critical thinking assessment in philosophy, you might create a large set of items that all pertain to critical thinking and then randomly split the questions up into two sets (forms A and B), which would represent the equivalent forms. One group of students gets form "A" first, then "B" with the second administration perhaps coming a week after the first. Another group takes the "B" form of the test first, then the "A" version with the second administration perhaps coming a week after the first. The scores on both are then correlated, producing a correlation or reliability coefficient as well as the stability of the scores.