ASSESSMENT WISE
Tools Evaluation
Basic Statistical Terms for Assessment Analysis
To evaluate a psychometric test, basic knowledge of statistics is essential. When standardized tests are used, understanding some statistical terms can help us interpret the results accurately.
Evaluation of an assessment tool
A good test should be supported by statistical and empirical evidence which shows both the test’s reliability and their validity.
Reliability is the trustworthiness or consistency of a measure. In other words, that is the degree to which a test or other measurement instrument is free of random error, yielding the same results across multiple applications to the same sample.
Validity shows whether a test is measuring what it intends to measure. There are three major types of validity.
Reliability
-
Internal consistency reliability
-
Test-retest reliability
-
Parallel-form reliability
-
Interrater reliability
A acceptable reliability (moderate reliability) should be >0.70.
Validity
-
Content Validity
-
Face Validity
-
Construct Validity
-
Criterion-related validity
Standard validity standards are 0.3 to 0.5.