ERIC Number: ED079345
Record Type: RIE
Publication Date: 1956-Jun
Reference Count: 0
How Accurate Is a Test Score?
Doppelt, Jerome E.
Test Service Bulletin, n50 p1-3 Jun 1956
The standard error of measurement as a means for estimating the margin of error that should be allowed for in test scores is discussed. The true score measures the performance that is characteristic of the person tested; the variations, plus and minus, around the true score describe a characteristic of the test. When the standard deviation is used as a measure of the variation of observed scores around the true score, the result is called the standard error of measurement. The standard error of measurement can be used in defining limits around the observed score within which one would be reasonably sure to find the true score. Since, in practice, it is not possible to give a large number of equivalent forms of a test in order to find the characteristic standard error of measurement, it is determined by the reliability coefficient. As measured by the reliability coefficient, reliability means consistency of measurement. It is unfortunately true that a test will have different reliability coefficients depending on the groups of people tested. The standard error of measurement is less subject to this variation. The formula for computing it, which is given, takes into account both the reliability coefficient and the standard deviation for each group. A table is provided of Standard Errors of Measurement for Given Values of Reliability Coefficient and Standard Deviation. (For related document, see TM 002 943, 946.) (DB)
Publication Type: N/A
Education Level: N/A
Authoring Institution: Psychological Corp., New York, NY.
Note: Reprint from Test Service Bulletin