About Still Nonignorable Consequences of (Partially) Ignoring Missing Item Responses in Large-scale Assessment

Alexander Robitzsch

No hmy45, OSF Preprints from Center for Open Science

Abstract: In recent literature, alternative models for handling missing item responses in large-scale assessments are proposed. In principle, based on simulations and arguments based test theory (Rose, 2013). In those approaches, it is argued that missing item responses should never be scored as incorrect, but rather treated as ignorable (e.g., Pohl et al., 2014). The present contribution shows that these arguments have limited validity and illustrates the consequences in a country comparison in the PIRLS 2011 study. A different treatment of missing item responses than recoding them as incorrect leads to significant changes in country rankings, which induces nonignorable consequences regarding the results' validity. Additionally, two alternative item response models based on different assumptions for missing item responses are proposed.

Date: 2020-10-20
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://osf.io/download/5f8f3c19054378000b827031/

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:osf:osfxxx:hmy45

DOI: 10.31219/osf.io/hmy45

Access Statistics for this paper

More papers in OSF Preprints from Center for Open Science
Bibliographic data for series maintained by OSF ().