Validity
What is "the degree that evidence and theory support information inferred in testing?"
Three steps should be taken.
What is "how many steps test developers should take to ensure a test's validity?"
Reliability
What is the synonym for consistency, when considering the "Big R" of testing?
A problem, or inconsistency that needs to be addressed in testing.
What is a "wrinkle" in reliability?
Inference and Interpretation.
What is "the labels given to a conclusion based on knowledge and skills in testing?"
What is "the steps are required to build a validity argument for an educational test?"
Within the test.
What is "where does reliability reside?"
Three significant wrinkles.
What is "how many wrinkles in testing should be ironed out?"
Accuracy and alliance to the purpose deemed.
What does testing validity rely on?
Isolate the purpose and identify inference-accuracy evidence,
What is "the steps to prove the suitability of an educational test?"
Score similarity from one day to the next.
What is test-retest reliability evidence?
What is the consistency of the decisions made based on a student's score?
A collection of validation evidence supported by score based inferences of a test's primary purpose.
What is a validity argument?
The process a validity argument should mirror, stating the most pertinent evidence to support accuracy and purpose.
What is akin to the closing argument in a trial?
Constant results from two or more different forms of an assessment.
What is alternate from reliability evidence?
A measurement used when considering consistency of a student's performance on multiple attempts of a given test.
What is the standard error of measurement?
This test is "valid".
What is the "loose language" for evidence of a test's scores being accurate and consistent with the test's purpose?
What is "how test validation should be perceived?"
Ensuring all test items are measuring the same thing.
What is Internal consistency reliability evidence?
Using a reliability coefficient along with standard deviation.
What is the calculation of a standard error of measurement to make student based decisions?