ABSTRACT
The object of this chapter is to describe some applications of reliability theory. The first section deals with the effect on reliability of shortening or lengthening a test—dropping or adding items. The next section contains a review of the choices of scale available for a test score and relates these to the scaling of the attribute and of the error of measurement and its variance. The following section deals with the estimation of a true score and the error of estimate. Then a section treats the problem of estimating relationships between true scores on two or more tests—“attenuation” problems. A final section deals with error in the measurement of differences.
