Hill CD, Edwards MC, Thissen D, et al. Practical issues in the application of item response theory: a demonstration using items from the Pediatric Quality of Life Inventory (PedsQL) 4.0 Generic Core Scales. Med Care.45(Suppl 1):S39-S47

RTI Health Solutions, Research Triangle Park, North Carolina 27709-2194, USA.
Medical Care (Impact Factor: 2.94). 06/2007; 45(5 Suppl 1):S39-47. DOI: 10.1097/01.mlr.0000259879.05499.eb
Source: PubMed

ABSTRACT Item response theory (IRT) is increasingly being applied to health-related quality of life instrument development and refinement. This article discusses results obtained using categorical confirmatory factor analysis (CCFA) to check IRT model assumptions and the application of IRT in item analysis and scale evaluation.
To demonstrate the value of CCFA and IRT in examining a health-related quality of life measure in children and adolescents.
This illustration uses data from 10,241 children and their parents on items from the 4 subscales of the PedsQL 4.0 Generic Core Scales. CCFA was applied to confirm domain dimensionality and identify possible locally dependent items. IRT was used to assess the strength of the relationship between the items and the constructs of interest and the information available across the latent construct.
CCFA showed generally strong support for 1-factor models for each domain; however, several items exhibited evidence of local dependence. IRT revealed that the items generally exhibit favorable characteristics and are related to the same construct within a given domain. We discuss the lessons that can be learned by comparing alternate forms of the same scale, and we assess the potential impact of local dependence on the item parameter estimates.
This article describes CCFA methods for checking IRT model assumptions and provides suggestions for using these methods in practice. It offers insight into ways information gained through IRT can be applied to evaluate items and aid in scale construction.

1 Follower
  • Source
    • "& RMSEA > .08), modification indices, standardized residuals (see, for example, Hill et al., 2007), and discussions among the authors about possible item dependencies were used to inform the fitting of bi-factor models, which take into account plausible patterns of residual item correlations thus maintaining a general unidimensional executive function construct. "
    [Show abstract] [Hide abstract]
    ABSTRACT: This study demonstrates the merits of evaluating a newly developed battery of executive function tasks, designed for use in early childhood, from the perspective of item response theory (IRT). The battery was included in the 48-month assessment of the Family Life Project, a prospective longitudinal study of 1292 children oversampled from low-income and African American families. IRT models were applied to a select set of tasks to demonstrate empirically (a) a principled method for item evaluation, including the utility of item characteristic curves; (b) how to explicitly test whether the measurement properties of executive function tasks are invariant across mutually exclusive subgroups of youths; (c) how the precision of measurement of a given task can vary according to underlying child ability; and (d) the utility of using IRT-based versus percentage correct scores. Results are discussed with respect to the importance of developing psychometrically sound and scalable instruments that facilitate the measurement of interindividual differences in intraindividual change of executive function across the early childhood period.
    Journal of Experimental Child Psychology 03/2011; 108(3):414-35. DOI:10.1016/j.jecp.2010.04.007 · 3.12 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: A scale measuring quality of life (QOL) is important in adolescent research. Using the graded response model (GRM), this study evaluates the psychometric properties of the satisfaction ratings of the Quality of Life Profile Adolescent Version (QOLPAV). Data for 1,392 adolescents were used to check IRT assumptions such as unidimensionality and local item dependence (LID). The goodness of fit of the GRM to the data and the item characteristic curves were evaluated. The reliability and validity analyses included item/test information, Cronbach’s α, and convergent and discriminant validity. Differential item functioning (DIF) procedures were also performed to detect item bias. The results provide evidence that the items sufficiently measured one single dimension. Few pairs of questions were flagged as LID due to content or wording similarity. Five items did not fit the GRM, and 4 were low in item discrimination. The findings also suggest that the assessment had appropriate reliability and validity. The DIF impact on the assessment score was considered minor. Because QOLPAV includes a respondent’s perceived importance of various life aspects, a short form that only considers important life aspects in the overall QOL estimation for each respondent becomes feasible within the framework of IRT. Future studies focusing on the development of a QOL overall index using the items from QOLPAV are recommended.
    Social Indicators Research 01/2011; 110(1). DOI:10.1007/s11205-011-9935-1 · 1.40 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: A new mathematical model of the myelinated nerve fiber was applied to the study of conduction behavior. This model represents the myelinated nerve fiber as a multiaxial equivalent electric circuit incorporating separate intra-axonal, periaxonal and extra-axonal longitudinal conductive pathways with independent representations of the myelin sheath versus the underlying axolemmal membrane. A detailed anatomical representation of the node is included, with the periaxonal space extending to the nodal compartment. Both amphibian and mammalian nerve fibers were modeled. Model results show a physiological conduction velocity of 57.6 m/s for 17.5-μm-diameter mammalian nerve fiber at 37°C with a change in conduction velocity versus temperature closely correlated to experimental findings. The periaxonal space width and the axon radius in the paranodal region are shown to have a strong influence on conduction velocity
    Engineering in Medicine and Biology Society, 1989. Images of the Twenty-First Century., Proceedings of the Annual International Conference of the IEEE Engineering in; 12/1989
Show more


1 Download
Available from