ERIC Identifier: ED315430
Publication Date: 1989-08-00
Source: ERIC Clearinghouse on Tests Measurement
and Evaluation Washington DC., American Institutes for Research Washington DC.
A Glossary of Measurement Terms. ERIC Digest.
Achievement Test--an objective examination that measures educationally
relevant skills or knowledge about such subjects as reading, spelling, or
Age Norms--values representing typical or average performance of people of
Average--a statistic that indicates the central tendency or most typical
score of a group of scores. Most often average refers to the sum of a set of
scores divided by the number of scores in the set.
Battery--a group of carefully selected tests that are administered to a given
population, the results of which are of value individually, in combination, and
Ceiling--the upper limit of ability that can be measured by a particular
Criterion-Referenced Test--a measurement of achievement of specific criteria
or skills in terms of absolute levels of mastery. The focus is on performance of
an individual as measured against a standard or criteria rather than against
performance of others who take the same test, as with norm-referenced tests.
Diagnostic Test--an intensive, in-depth evaluation process with a relatively
detailed and narrow coverage of a specific area. The purpose of this test is to
determine the specific learning needs of individual students and to be able to
meet those needs through regular or remedial classroom instruction.
Domain-Referenced Test--a test in which performance is measured against a
well-defined set of tasks or body of knowledge (domain). Domain-referenced tests
are a specific set of criterion-referenced tests and have a similar purpose.
Grade Equivalent--the estimated grade level that corresponds to a given
Informal Test--a nonstandardized test that is designed to give an approximate
index of an individual's level of ability or learning style; often
Inventory--a catalog or list for assessing the absence or presence of certain
attitudes, interests, behaviors, or other items regarded as relevant to a given
Item--an individual question or exercise in a test or evaluative instrument.
Norm--performance standards that is established by a reference group and that
describes average or typical performance. Usually norms are determined by
testing a representative group and then calculating the group's test
Normal Curve Equivalent--standard scores with a mean of 50 and a standard
deviation of approximately 21.
Norm-Referenced Test--an objective test that is standardized on a group of
individuals whose performance is evaluated in relation to the performance of
others; contrasted with criterion-referenced test.
Objective Percent Correct--the percent of the items measuring a single
objective that a student answers correctly.
Percentile--the percent of people in the norming sample whose scores were
below a given score.
Percent Score--the percent of items that are answered correctly.
Performance Test--designed to evaluate general intelligence or aptitudes.
Consists primarily of motor items or perceptual items because verbal abilities
play a minimal role.
Published Test--a test that is publicly available because it has been
copyrighted and published commercially.
Rating Scales--subjective assessments made on predetermined criteria in the
form of a scale. Rating scales include numerical scales or descriptive scales.
Forced choice rating scales require that the rater determine whether an
individual demonstrates more of one trait than another.
Raw Score--the number of items that are answered correctly.
Reliability--the extent of which a test is dependable, stable, and consistent
when administered to the same individuals on different occasions. Technically,
this is a statistical term that defines the extent of which errors of
measurement are absent from a measurement instrument.
Screening--a fast, efficient measurement for a large population to identify
individuals who may deviate in a specified area, such as the incidence of
maladjustment or readiness for academic work.
Specimen Set--a sample set of testing materials that are available from a
commercial test publisher. May include a complete individual test without
multiple copies or a copy of the basic test and administration procedures.
Standardized Test--a form of measurement that has been normed against a
specific population. Standardization is obtained by administering the test to a
given population and then calculating means, standard deviations, standardized
scores, and percentiles. Equivalent scores are then produced for comparisons of
an individual score to the norm group's performance.
Standard Scores--a score that is expressed as a deviation from a population
Stanine--one of the steps in a nine-point scale of standard scores.
Validity--the extent to which a test measures what it was intended to
measure. Validity indicates the degree of accuracy of either predictions or
inferences based upon a test score.