Comparison of several small sample equating methods under the NEAT design


Creative Commons License

Caglak S.

TURKISH JOURNAL OF EDUCATION, vol.5, no.3, pp.96-118, 2016 (Journal Indexed in ESCI) identifier

  • Publication Type: Article / Article
  • Volume: 5 Issue: 3
  • Publication Date: 2016
  • Doi Number: 10.19128/turje.16916
  • Title of Journal : TURKISH JOURNAL OF EDUCATION
  • Page Numbers: pp.96-118

Abstract

The aim of this study is to compare the performances of Identity, Nominal Weights Mean (NMW), and Circle-Arc (CA) equating methods under the Non-Equivalent Groups Anchor-Test (NEAT) design. Synthetic equating functions (SFs) of the NWM and CA (NWS and CAS) were also created using an equal weighting system (w = 0.5). Different sizes of small examinee samples (n = 10, 20, 50, 100) were used to equate new test forms to base test forms. Chained Equipercentile (CE) with bivariate log-linear presmoothing was used as population criterion equating function to compare the performances of the equating methods. Overall, the identity (ID) equating was the most favorable, but the NWS method produced less equating error than the ID and Tucker Linear (TL) equating methods under specific simulation conditions. The use of the SF of the NWM method can be used in practice to equate the test forms with samples less than 25 examinees. In future studies, the SFs of other existing equating methods should be tested to determine the best performing equating method(s) for small sample equating.