30

# Dependent Measures

The outcome or dependent variables in this study are comprised of test scores

calculated in two ways. Reading and Math scores exist in the data set as individual

standardized T-scores described in the ELS 2002 Codebook as:

The standardized T score provides a norm-referenced measurement of achievement, that is, an estimate of achievement relative to the population (spring 2002 10th graders) as a whole. It provides information on status compared to peers (as distinguished from the IRT-estimated number-right score which represents status with respect to achievement on a particular criterion set of test items). The standardized T score is a transformation of the IRT theta (ability) estimate, rescaled to a mean of 50 and standard deviation of 10 (P.35-9).

# A third test score variable is a composite created which combines scores for Reading

and Math. According to the ELS 2002 Codebook:

The composite score is the average of the math (BYTXMSTD) and reading (BYTXRSTD) standardized scores, re-standardized to a national mean of 50.0 and standard deviation of 10.0. Some students had scores for only the math test or reading test, but not both. For these students who did not have both scores, the composite is based on the single score that was available. The standardized T score provides a norm-referenced measurement of achievement, that is, an estimate of achievement relative to the population (spring 2002 10th graders) as a whole. It provides information on status compared to peers (as distinguished from the IRT-estimated number-right score which represents status with respect to achievement on a particular criterion set of test items) (P.32).

# For the standardized Reading, standardized Math, and Composite variable, scores

range from a low of 20.91 to a high of 78.76 points. The standard deviation for all three

categories ranges from 9.96 to 9.98 (N = 15,362). In addition to these measures, this

study will include one outcome variable from the first follow-up conducted in 2004.

# Although the study already has one composite math score variable, the first follow-up

math composite variable (N=15,325) is the best available variable to address the issue of