This article briefly describes the research (Botta, 2021) that led to the construction and field administration of the first multilevel adaptive test (MST Test) in Italy and reports the results of a new research project that aimed at verifying ex-post the measurement properties of the constructed test. The test was designed for the estimation of students' abilities in mathematics in grade 10 and was administered to a sample of 4,132 students. In the paper, we analyze with two paired-samples t-tests the changes in the mean of the students' ability estimation and the changes in the relative standard error of the mean as they move from the first to the last level of the test. The results demonstrate the validity of the adaptive algorithm underlying the implementation of the test. The results obtained are also a further empirical verification that in an MST test the calculation of the true score is sufficiently accurate for the purpose of selecting the next testlet, as stated by Luecht and Nungester (1998).

Verification of the Measurement Properties of an MST Test: An Alternative Ex-Post Approach

EMANUELA BOTTA
2022-01-01

Abstract

This article briefly describes the research (Botta, 2021) that led to the construction and field administration of the first multilevel adaptive test (MST Test) in Italy and reports the results of a new research project that aimed at verifying ex-post the measurement properties of the constructed test. The test was designed for the estimation of students' abilities in mathematics in grade 10 and was administered to a sample of 4,132 students. In the paper, we analyze with two paired-samples t-tests the changes in the mean of the students' ability estimation and the changes in the relative standard error of the mean as they move from the first to the last level of the test. The results demonstrate the validity of the adaptive algorithm underlying the implementation of the test. The results obtained are also a further empirical verification that in an MST test the calculation of the true score is sufficiently accurate for the purpose of selecting the next testlet, as stated by Luecht and Nungester (1998).
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11697/225867
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact