Comparison of Traditional and Item Response Theory Methods for Equating Tests

Kolen, Michael J.

doi:10.1111/j.1745-3984.1981.tb00838.x

Cited by 89 publications

(85 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Hence, it seems that the choice of the 2PL model over the 1PL model would occasionally lead to a practically significant difference in equating for this test; however, even this practically significant difference is not a huge difference. The 1PL model has often been found to lead to poor equating results (see, for example, Kolen, 1981;Lu & Smith, 2007).…”

Section: The Practical Significance Of Misfitmentioning

confidence: 99%

Fit of Item Response Theory Models: A Survey of Data From Several Operational Tests

Sinharay

Haberman

Jia

2011

ETS Research Report Series

View full text Add to dashboard Cite

show abstract

Section: The Practical Significance Of Misfitmentioning

confidence: 99%

Fit of Item Response Theory Models: A Survey of Data From Several Operational Tests

Sinharay

Haberman

Jia

2011

ETS Research Report Series

View full text Add to dashboard Cite

show abstract

“…In a study by Harris (1991), IRT true score equating did not provide better results than did equipercentile methods. Kolen (1981) compared true score and observed score IRT equating for both the one-, two-, and three-parameter model to traditional equipercentile linear methods for two tests. No method turned out to be superior, although in general, the equating based on IRT models yielded better results.…”

Section: Developmental Score Scales and Vertical Equatingmentioning

confidence: 99%

Investigating the Dimensions of Spelling Ability

Notenboom¹,

Reitsma

2003

Educational and Psychological Measurement

View full text Add to dashboard Cite

In this study, the latent structure of a spelling achievement test for elementary school grades was investigated. Factor analyses revealed that for Grades 2 to 6, the test was unidimensional, whereas for Grade 1, two factors were found: a phonological factor and an orthographic factor. Because of the anchor-test design, vertical equatingwas required to fit a two-parameter, unidimensional item response theory model. Concurrent calibration of the parameters, implemented in BILOG–Multiple Groups (MG), was used as the linking procedure. An evaluation of the model showed that invariant parameter estimates and ability scores were obtained. The transition from an alphabetic to an orthographic strategy occurs in the first grade. Learning to spell throughout elementary education mainly consists of learning to apply orthographic knowledge.

show abstract

“…Lord (1977Lord ( , 1980 observed that equipercentile equating of 0 observed formula scores yielded results somewhat different from those based on IRT equating procedures; the two IRT methods, however, yielded very similar results. Kolen (1981) observed that equating methods based on the three-parameter model were more stable (in terms of cross-validation) than were other IKT and conventional methods. Similarly, three-parameter IRT methods worked better than conve-tional S methods for equating nonparallel tests in the study by Petersen et al (1983).…”

Section: Resultsmentioning

confidence: 95%

“…Some studies (Beard & Pettie, 1979;Golub-Smith, 1980;Modu, 1982;Rentz & Bashaw, 1975 found no differences among methods, while others (Bejar & Wingersky, 1981Hicks, 1983;Kolen, 1981;Kolen & Whitney, 1982;Lord, 1977Lord, , 1980Marco, 1977;Marco et al, 1980;Petersen et al, 1983;Phillips, 1983) found that the methods ordered themselves differently depending upon the conditions under which equating was performed and the results were .. '. , --evaluated.…”

Section: Resultsmentioning

confidence: 99%