The Most Appropriate Scores for Measuring Educational Development in the Elementary Schools: GE's

The Influence of Reading on Vocabulary Growth: A Case for a Matthew Effect

“…The rationale for the use of IRT-based scores was that they appear to have the best properties, such as an equalappearing interval scale, for characterizing the growth of mental abilities. Concerns have been raised as to whether these scores are likely to show declining variance with increases in age, whereas grade-equivalence scores seem to produce increasing variance (e.g., Hoover, 1984;Yen, 1986). These patterns, however, have not been consistently reproduced (Williams, Pommerich, & Thissen, 1998), and it remains unclear whether, or under what circumstances, IRT scores or other forms of developmental scores misrepresent the changes in ability over time.…”

“…These patterns, however, have not been consistently reproduced (Williams, Pommerich, & Thissen, 1998), and it remains unclear whether, or under what circumstances, IRT scores or other forms of developmental scores misrepresent the changes in ability over time. Nonetheless, the use of IRT (Rasch) scores has been critiqued in investigations of a Matthew effect fan spread (Bast & Reitsma, 1998;Stanovich, 2000) on the grounds that forcing within-age scores into a normal distribution could cause a decrease in developmental score variance with age (Hoover, 1984). For example, Stanovich (2000) proposed that the use of developmental ability scores could account for the compensatory effect found for reading scores in the study by Shaywitz et al (1995).…”

Models for Value-Added Modeling of Teacher Effects

“…[See (Rowan et al, 2002) and (Puma, Karweit, Price, Ricciuti, Thompson, & Vaden-Kiernan, 1997) for details on the Prospects data.] More generally there is considerable debate in the measurement community on the appropriate behavior of variability over time on true developmental scales (Burket, 1984;Hoover, 1984aHoover, , 1984bYen, 1986). Thus, the fit of the CC or layered models to some data sets will be poor.…”

Evaluating Value-Added Models for Teacher Accountability

“…RAND Clearly, these two scales do not suggest the same inferences about performance. This striking difference in variance trends sparked a sharp debate in the psychometrics field (see, e.g., Burket, 1984;Hoover, 1984aHoover, , 1984bYen, 1986) over what scale more accurately represented the domain about which inferences are intended and what type of variance trends was most plausible for the inferences that achievement tests are designed to support (Hoover, 1988, andYen, 1988).…”

“…While the range of possible scales is theoretically unlimited, only a few are widely used in modern measurement of achievement, and the cross-sectional relationships among these few are typically very strong. Thus, Hoover (1984a) noted that the purportedly interval developmental standard scores of some test publishers have nearly perfect cross-sectional correlation with the grade equivalent scale, which is expected not to be interval. 16 The high correlation between alternative scales is illustrated in Figure 4.1, which compares two common types of scaled scores from an algebra test administered to secondary school students by the College Board as part of its Equity 2000 project.…”