ABSTRACT
Based on concerns about the item response theory (IRT) linking approach used in the Programme for International Student Assessment (PISA) until 2012 as well as the desire to include new, more complex, interactive items with the introduction of computer-based assessments, alternative IRT linking methods were implemented in the 2015 PISA round. The new linking method represents a concurrent calibration using all available data, enabling us to find item parameters that maximize fit across all groups and allowing us to investigate measurement invariance across groups. Apart from the Rasch model that historically has been used in PISA operational analyses, we compared our method against more general IRT models that can incorporate item-by-country interactions. The results suggest that our proposed method holds promise not only to provide a strong linkage across countries and cycles but also to serve as a tool for investigating measurement invariance.
Disclosure statement
No potential conflict of interest was reported by the authors.
Notes
1. Plausible values are multiple imputations drawn from a posterior distribution obtained from a latent regression model (also referred to as population modeling or conditioning model) using IRT item parameters from the cognitive assessment and principal components from the student background questionnaire. In PISA, each respondent receives 10 plausible values for each cognitive domain that can be used as test scores to produce group level statistics (never as individual test scores). For more information on plausible values and population modeling see Mislevy et al. (1992), von Davier et al. (Citation2009), von Davier et al. (Citation2006) or Yamamoto et al. (Citation2013, updated 2016).
Additional information
Notes on contributors
Matthias von Davier
Matthias von Davier: Senior Research Director, ETS
Kentaro Yamamoto
Kentaro Yamamoto: Principal Research Scientist, ETS
Hyo Jeong Shin
Hyo Jeong Shin: Associate Research Scientist, ETS
Henry Chen
Henry Chen: Senior Research Scientist, ETS
Lale Khorramdel
Lale Khorramdel: Managing Research Scientist, ETS
Jon Weeks
Jon Weeks: Associate Research Scientist, ETS
Scott Davis
Scott Davis: Principal Research Data Analyst, ETS
Nan Kong
Nan Kong: Senior Research Data Analyst, ETS
Mat Kandathil
Mat Kandathil: Manager Data Analysis, ETS.