Latent trait models and dichotomization of graded responses

Jansen, Paul; Roskam, Edward E.

doi:10.1007/bf02294001

Cited by 55 publications

(45 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, compared with the dichotomized version of the item, the item information function of a polytomously scored item is higher at the peak of the function and the information is also distributed across a wider range of 0, which may also enhance the assessment of person fit (Reise & Due, 1991). Finally, the dichotomization that is chosen for a polytomous score variable has a substantial effect on the measurement outcome 0, unless specific conditions on the item parameters hold (Jansen & Roskam, 1986, Roskam & Jansen, 1989). …”

Section: Person-fit Analysismentioning

confidence: 99%

Detection of Person Misfit in Computerized Adaptive Tests with Polytomous Items

Krimpen-Stoop¹,

Meijer

2002

Applied Psychological Measurement

View full text Add to dashboard Cite

Item scores that do not fit an assumed item response theory model may cause the latent trait value to be estimated inaccurately. For computerized adaptive tests (CAT) with dichotomous items, several person-fit statistics for detecting nonfitting item score patterns have been proposed. Both for paper-and-pencil (P&P) test and CATs, detection of person misfit with polytomous items has hardly been explored. In this simulation study, the theoretical and empirical null distributions of a person-fit statistic for polytomous items are compared for P&P tests and CATs. Results show that the empirical distribution of this statistic was close to the standard normal distribution, for both P&P tests and CATs. Also statistics that are especially designed for a CAT are proposed. In these statistics observed and expected item scales are compared using cumulative sum (CUSUM) procedures.

show abstract

Section: Person-fit Analysismentioning

confidence: 99%

Detection of Person Misfit in Computerized Adaptive Tests with Polytomous Items

Krimpen-Stoop¹,

Meijer

2002

Applied Psychological Measurement

View full text Add to dashboard Cite

show abstract

“…Jansen & Roskam (1986) correctly distinguish between joining categories before and after the data are collected, and the example above illustrates joining before the data are collected. Whether or not data conform to the joining assumption is an empirical matter, but if the joining assumption is expected or required to hold, then the Thurstone model, rather than the Rasch model, is the relevant model.…”

mentioning

confidence: 97%

Distinctive and Incompatible Properties of Two Common Classes of IRT Models for Graded Responses

Andrich

1995

Applied Psychological Measurement

View full text Add to dashboard Cite

same Rasch model with the smaller number of categories. These differences imply that the choice between these two classes of models for graded responses is not simply a matter of preference; they also permit a better understanding of the choice of models for graded response data as a function of the underlying processes they are intended to represent. Index terms: graded responses, joining assumption, polytomous IRT models, Rasch model, Thurstone model. The collection of data in the form of graded responses is ubiquitous in the social sciences (Dawes, 1972); it is used when measurement of the kind used in the physical sciences would be desirable, but no such relevant measuring instrument exists. The prototype of measurement is the partitioning of a continuum, abstracted as the real number line, by equidistant thresholds sufficiently fine that their own width can be ignored, and the location of an entity or object on this line with the use of an instrument. The location of the entity or object, typically called the measurement, is the number of thresholds exceeded by the object from the origin, and is defined in the unit of the common distance between the thresholds. Although measuring instruments have operating ranges, a measurement is not taken to be a function of the operating range of any instrument-instead, if a measurement is contaminated by the operating range of the instrument (e.g., floor or ceiling effects), another instrument with a range more compatible with the location of the entity or object is sought. In addition, all measurements involve error. However, in deterministic frameworks, it is assumed that the error is sufficiently small relative to the measurements that the error can be ignored. This paper draws on this prototype of measurement in analyzing models for graded responses. Measurement in the Social SciencesGraded response formats in the social sciences mirror measurement in the physical sciences in that the entity-the person being measured on a given variable-is postulated to be located on a latent continuum

show abstract

“…However, the collapsing of adjacent categories in this way destroys the structure of the PRM (Rasch, 1966;Andersen, 1977;Andrich 1978Andrich , 1995Jansen & Roskam, 1986). Wilson and Masters (1993) proposed a procedure whereby they retained the structure of the model in the presence of categories with zero frequencies, but that meant that the adjacent thresholds which defined a category could not be estimated.…”

Section: The Structure Of the Prm And Categories With Zero Frequenciesmentioning

confidence: 98%

Sufficiency and Conditional Estimation of Person Parameters in the Polytomous Rasch Model

Andrich

2010

Psychometrika

View full text Add to dashboard Cite

show abstract

Latent trait models and dichotomization of graded responses

Abstract: latent trait theory, dichotomization, polychotomous Rasch model, graded responses, rating data,

Cited by 55 publications

References 19 publications

Detection of Person Misfit in Computerized Adaptive Tests with Polytomous Items

Detection of Person Misfit in Computerized Adaptive Tests with Polytomous Items

Distinctive and Incompatible Properties of Two Common Classes of IRT Models for Graded Responses

Sufficiency and Conditional Estimation of Person Parameters in the Polytomous Rasch Model

Contact Info

Product

Resources

About