Dataset Information

Investigating the Practical Consequences of Model Misfit in Unidimensional IRT Models.

ABSTRACT: In this article, the practical consequences of violations of unidimensionality on selection decisions in the framework of unidimensional item response theory (IRT) models are investigated based on simulated data. The factors manipulated include the severity of violations, the proportion of misfitting items, and test length. The outcomes that were considered are the precision and accuracy of the estimated model parameters, the correlations of estimated ability ([Formula: see text]) and number-correct ([Formula: see text]) scores with the true ability ([Formula: see text]), the ranks of the examinees and the overlap between sets of examinees selected based on either [Formula: see text], [Formula: see text], or [Formula: see text] scores, and the bias in criterion-related validity estimates. Results show that the [Formula: see text] values were unbiased by violations of unidimensionality, but their precision decreased as multidimensionality and the proportion of misfitting items increased; the estimated item parameters were robust to violations of unidimensionality. The correlations between [Formula: see text], [Formula: see text], and [Formula: see text] scores, the agreement between the three selection criteria, and the accuracy of criterion-related validity estimates are all negatively affected, to some extent, by increasing levels of multidimensionality and the proportion of misfitting items. However, removing the misfitting items only improved the results in the case of severe multidimensionality and large proportion of misfitting items, and deteriorated them otherwise.

SUBMITTER: Crisan DR

PROVIDER: S-EPMC5533251 | biostudies-literature | 2017 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Investigating the Practical Consequences of Model Misfit in Unidimensional IRT Models.

Crişan Daniela R DR Tendeiro Jorge N JN Meijer Rob R RR

Applied psychological measurement 20170317 6

In this article, the <i>practical</i> consequences of violations of unidimensionality on selection decisions in the framework of unidimensional item response theory (IRT) models are investigated based on simulated data. The factors manipulated include the severity of violations, the proportion of misfitting items, and test length. The outcomes that were considered are the precision and accuracy of the estimated model parameters, the correlations of estimated ability ([Formula: see text]) and num ...[more]

PMID: 28804181

Similar Datasets

Project description:BackgroundCOVID-19 has led to the adoption of unprecedented mitigation measures which could trigger many unintended consequences. These unintended consequences can be far-reaching and just as important as the intended ones. The World Health Organization identified the assessment of unintended consequences of COVID-19 mitigation measures as a top priority. Thus far, however, their systematic assessment has been neglected due to the inattention of researchers as well as the lack of training and practical tools.Main textOver six years our team has gained extensive experience conducting research on the unintended consequences of complex health interventions. Through a reflexive process, we developed insights that can be useful for researchers in this area. Our analysis is based on key literature and lessons learned reflexively in conducting multi-site and multi-method studies on unintended consequences. Here we present practical guidance for researchers wishing to assess the unintended consequences of COVID-19 mitigation measures. To ensure resource allocation, protocols should include research questions regarding unintended consequences at the outset. Social science theories and frameworks are available to help assess unintended consequences. To determine which changes are unintended, researchers must first understand the intervention theory. To facilitate data collection, researchers can begin by forecasting potential unintended consequences through literature reviews and discussions with stakeholders. Including desirable and neutral unintended consequences in the scope of study can help minimize the negative bias reported in the literature. Exploratory methods can be powerful tools to capture data on the unintended consequences that were unforeseen by researchers. We recommend researchers cast a wide net by inquiring about different aspects of the mitigation measures. Some unintended consequences may only be observable in subsequent years, so longitudinal approaches may be useful. An equity lens is necessary to assess how mitigation measures may unintentionally increase disparities. Finally, stakeholders can help validate the classification of consequences as intended or unintended.ConclusionStudying the unintended consequences of COVID-19 mitigation measures is not only possible but also necessary to assess their overall value. The practical guidance presented will help program planners and evaluators gain a more comprehensive understanding of unintended consequences to refine mitigation measures.

Dataset Information

Investigating the Practical Consequences of Model Misfit in Unidimensional IRT Models.

Publications

Investigating the Practical Consequences of Model Misfit in Unidimensional IRT Models.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets