Comparison of item characteristic analysis models of reading literacy test with polytomous Item Response Theory

Firyal Nabila Harsana (Universitas Negeri Yogyakarta)
Heri Retnawati (Universitas Negeri Yogyakarta)
Septinda Rima Dewanti (Queensland University of Technology)
Rogers Andrew Lumenyela (Institute of Rural Development Planning)
Rimajon Sotlikova (Webster University in Tashkent)
Maulana Fatahillah Adzima (University of California Berkeley)
Atut Reni Septiana (University of Manchester)

REiD (Research and Evaluation in Education)
Vol. 10 No. 2 (2024)

This study aims to compare the analysis model of the characteristics of reading literacy items with the polytomous item response theory, which uses the Graded Response Model (GRM), Partial Credit Model (PCM), Generalized Partial Credit Model (GPCM), and Nominal Reasons Model (NRM). This research is quantitative research in nature, and secondary data were used from about 1000 test takers' responses to reading literacy items in the 2018 reading literacy study analyzed with the R program. This model comparison was carried out so that the analysis results obtained were more accurate in representing the level of reading literacy skills in Indonesia. The results show that the GPCM model is the fit model with an AIC value of 23753.89 and a BIC value of 24042.45, and the number of suitable testlets is 7 out of a total of 7 testlets. Based on the relationship between information function scores and SEM, reading literacy items provide higher information when participants' abilities range between -2.3 and +2.