NotesFAQContact Us
Search Tips
ERIC Number: ED523926
Record Type: Non-Journal
Publication Date: 2010-Feb
Pages: 41
Abstractor: As Provided
Reference Count: 14
Chained versus Post-Stratification Equating in a Linear Context: An Evaluation Using Empirical Data. Research Report. ETS RR-10-06
Puhan, Gautam
Educational Testing Service
This study used real data to construct testing conditions for comparing results of chained linear, Tucker, and Levine-observed score equatings. The comparisons were made under conditions where the new- and old-form samples were similar in ability and when they differed in ability. The length of the anchor test was also varied to enable examination of its effect on the three different equating methods. Two tests were used in the study, and the three equating methods were compared to a criterion equating to obtain estimates of random equating error, bias, and root mean squared error (RMSE). Results showed that for most of the conditions studied, chained linear score equating produced fairly good equating results in terms of low bias and RMSE. In some conditions, Levine-observed score equating also produced low bias and RMSE. Although the Tucker method always produced the lowest random equating error, it produced a larger bias and RMSE than either of the other equating methods. Based on these results, it is recommended that either chained linear or Levine score equating be used when new- and old-form samples differ in ability and/or when the anchor-to-total correlation is not very high. Appended are: (1) Difference in new-form total-to-anchor relationship obtained using new- and old-form samples; (2) Difference in old-form total-to-anchor relationship obtained using new- and old-form samples; and (3) An example in which Tucker showed less bias than was shown by chained linear equating. (Contains 12 figures and 4 tables.)
Educational Testing Service. Rosedale Road Mailstop 19R, Princeton, NJ 08541-0001. Tel: 609-921-9000; Fax: 609-734-5410; Web site:
Publication Type: Reports - Research
Education Level: N/A
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: Educational Testing Service