Restricted Recalibration of Item Response Theory Models

Liu, Yang; Yang, Ji Seung; Maydeu-Olivares, Alberto

doi:10.1007/s11336-019-09667-4

Cited by 12 publications

(15 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, future studies should evaluate the reproducibility of the scale. Second, although in the process of adapting the scale, the functioning of the items was analyzed using a Rasch model, in the entire sample, the differential functioning of the items was not evaluated, so it is recommended to examine item performance with more robust models based on the item response theory (Liu et al, 2019).…”

Section: Discussionmentioning

confidence: 99%

Adaptation and psychometric evaluation of the Fear of COVID-19 Scale in the general Colombian population

2021

View full text Add to dashboard Cite

The study aimed to adapt and explore the psychometric performance of the Fear of COVID-19 Scale (FCV-19S) in the general Colombian population. The original FCV-19S is a 7-item scale that underwent an adaptation (Item 1 and 5 were deleted). From an online sample of 1,687 adults (59% female), exploratory and confirmatory factor analyses were performed for versions of the scale with 6 and 5 items. Cronbach's alpha and McDonald's omega were calculated. The confirmatory factor analysis showed that the 5-item scale (Fear of COVID-5) presented better indicators. In conclusion, the Fear of COVID-5 has acceptable performance in the Colombian population.

show abstract

Section: Discussionmentioning

confidence: 99%

Adaptation and psychometric evaluation of the Fear of COVID-19 Scale in the general Colombian population

2021

View full text Add to dashboard Cite

show abstract

“…It is assumed that the calibration sample for true ξ ^ 1 and true ξ ^ 2 is different from the evaluation sample. Liu et al (2019) described this conditional estimation problem as restricted recalibration (RR) and demonstrated that under the setup of RR, normalbold ω ^ − ω is asymptotically equivalent to…”

Section: Residual Methodsmentioning

confidence: 99%

“…With no subset partition, the residual becomes the standard statistic in evaluating model fit in the RR problem (Liu et al, 2019). The asymptotic residual variance for item i can be written as…”

Section: Residual Methods With No Partition Of S1 and S2mentioning

confidence: 99%

Detecting Compromised Items Using Information From Secure Items

Wang

Liu

2020

Journal of Educational and Behavioral Statistics

Self Cite

View full text Add to dashboard Cite

In continuous testing programs, some items are repeatedly used across test administrations, and statistical methods are often used to evaluate whether items become compromised due to examinees’ preknowledge. In this study, we proposed a residual method to detect compromised items when a test can be partitioned into two subsets of items: secure items and possibly compromised items. We derived the standard error of the residual statistic by taking the sampling error in both ability and item parameter estimate into account. The simulation results suggest that the Type I error is close to the nominal level when both sources of error are adjusted, and item parameter error can be ignored only when the item calibration sample size is much larger than the evaluation sample size. We also investigated the performance of the residual method when not using information from secure items in both simulation and real data analyses.

show abstract

“…The differential functioning of the items and the construct validity were not evaluated through models based on the item response theory that provide additional elements for the refinement of the scales [23]. However, having shorter versions of measurement instruments can offer some advantages in research and the clinical setting: blunt instruments are usually one-dimensional and show more reproducible psychometric indicators in different contexts [24].…”

Section: Strengths and Limitations Of The Studymentioning

confidence: 99%

Dimensionality and homogeneity of the Colombian version of the Cocaine Craving Questionnaire (CCQ-N-10)

Cassiani-Miranda

Scoppetta²,

Quintero-Gómez

et al. 2021

Preprint

View full text Add to dashboard Cite

Background and aim: It is essential to have a validated instrument to measure craving for cocaine use. However, in Colombia, there is no instrument to screen cocaine craving. The study aimed to determine the homogeneity and dimensionality of the CCQ-N-10 in patients with cocaine use disorder in Colombia. Materials and methods: An adaptation and subsequent analysis of the psychometric properties of the CCQ-N-10 scale was carried out with 102 hospitalized or outpatient adults diagnosed with substance use disorders in addiction units in Bucaramanga, Colombia. Internal consistency and construct validity were estimated by confirmatory factor analysis and correlation analysis with scales with similar objectives. Results: An omega coefficient of 0.93 was obtained, and adjustment indicators of the confirmatory model were acceptable (RMSEA of 0.08, CFI and TLI of 0.99) when two of the original scale items were removed from the original scale analysis. Conclusions: This study shows that the craving scale reduced to eight items can be helpful to assess the construct in the Colombian population; However, the small sample size makes it challenging to carry out other analyzes to corroborate its psychometric properties.

show abstract

Restricted Recalibration of Item Response Theory Models

Cited by 12 publications

References 61 publications

Adaptation and psychometric evaluation of the Fear of COVID-19 Scale in the general Colombian population

Adaptation and psychometric evaluation of the Fear of COVID-19 Scale in the general Colombian population

Detecting Compromised Items Using Information From Secure Items

Dimensionality and homogeneity of the Colombian version of the Cocaine Craving Questionnaire (CCQ-N-10)

Contact Info

Product

Resources

About