Minimally competent - This refers to a basic level of examinee proficiency that is determined to reflect acceptable performance for passing a given certification or licensure exam. The concept of minimal competency is used during standard setting to determine the passing score on the test.
Misclassification - This refers to the problem of classification errors that may occur in criterion-referenced testing, when the passing score is applied. In one type of misclassification, an examinee who is not minimally competent may still pass the test; in a second type of misclassification, an examinee who actually is competent, nevertheless fails the test. A primary goal of well-designed exam programs is to reduce misclassification as much as possible.
Modified Angoff - In this frequently used approach to standard setting a panel of judges is asked to review a test, one item at a time. Each judge gives an estimate of the proportion of a hypothetical group of minimally competent examinees that would be expected to respond to each item correctly. These proportions are then averaged across items and across judges to arrive at a recommended passing score for the test.
Multiple choice item - This is the most commonly used item type in standardized testing. Each multiple choice item typically consists of a prompt or stem, which may be in the form of a question or statement, followed by a set of four or five response options. The single correct response option is called the key, while the remaining, incorrect response options are called distractors.