When observed scores are randomly generated, they consist entirety of error. To define true scores as the expected value of observed scores in this instance, as Allen (this issue) did, is erroneous. Furthermore, it is possible to calculate a correlation coefficient without dividing by 0.
Get full access to this article
View all access options for this article.
References
1.
AllenM. J. (this issue). Comments on “A demonstration of measurement error and reliability.”Teaching of Psychology, 19, 111.
2.
AnastasiA. (1988). Psychological testing (6th ed.). New York: Macmillan.
3.
BuckJ. L. (1991). A demonstration of measurement error and reliability. Teaching of Psychology, 18, 46–47.
4.
CrockerL.AlginaJ. (1986). Introduction to classical and modern test theory. New York: Holt, Rinehart & Winston.
5.
GronlundN. E. (1981). Measurement and evaluation in teaching (4th ed.). New York: Macmillan.
6.
HopkinsC. D.AntesR. L. (1990). Classroom measurement and evaluation (3rd ed.). Itasca, IL: Peacock.
7.
LordR M.NovickM. R. (with contributions by A. Birnbaum). (1968). Statistical theories of mental test scores. Reading, MA: Addison-Wesley.
8.
RunyonR. B.HaberA. (1988). Fundamentals of behavioral statistics (6th ed.). New York: Random House.
9.
SaxG. (1980). Principles of educational and psychological measurement and evaluation (2nd ed.). Belmont, CA: Wadsworth.
10.
ThorndikeR. L. (1964). Reliability. In Proceedings of the 1963 Invitational Conference on Testing Problems. Princeton, NJ: Educational Testing Service.
