Validity
This characteristic of assessment refers to the degree to which score-based inferences are accurate and aligned to the intended purpose of the test.
What is validity?
This is a synonym for assessment reliability.
What is consistency?
The purpose of assessment is to measure a test-taker's underlying knowledge/skills through this metric.
What is a score based inference?
This analysis is provided as a justification of a score-based inference's level of alignment to an assessment's primary purpose.
What is a validity argument?
This reliability indicator represents the degree to which different versions of the same test are consistent in their level of difficulty & ability to measure the same thing.
What is alternate-form reliability?
This metric gives a numerical indication of the strength and direction of the relationship between two variables.
What is a correlation coefficient?
This professional can be recruited to conduct validity analyses for educational tests, and provide validation arguments in plain language that can be understood by all school stakeholders.
Who is a measurement specialist?
This reliability indicator represents the consistency among all the items of a test in what they measure.
What is internal-consistency reliability?
This indicator focuses on a test's ability to produce scores that yield the same ultimate decision as a result of student performance on that test.
What is a decision consistency estimate?
This is evidence that indicates whether a test can distinguish between well- and poorly-taught students; and should be included in the validity analysis of any test used to evaluate instructional quality.
What is instructional sensitivity?
This reliability indicator represents the stability with which an assessment measures what it is intended to across all test administrations.
What is test-retest reliability?
This metric provides a margin of error that allows test developers to discern the consistency of an individual student's performance.
What is standard error of measurement?
These are the first & second steps in the assessment validation process.
What are collecting evidence of a score-based inference's accuracy and fitness for purpose?
On a test that's intended to measure two distinct cognitive skills, we should NOT see this type of reliability evidence.
What is a strong, positive internal consistency coefficient?
This measure of score-spread among test takers allows test developers to calculate an SEM to be used when making test-based decisions about individual students.
What is standard deviation?