1993
DOI: 10.1177/0013164493053001005
|View full text |Cite
|
Sign up to set email alerts
|

Computerized Adaptive Testing Using the Partial Credit Model: Effects Of Item Pool Characteristics and Different Stopping Rules

Abstract: Simulated datasets were used to research the effects of the systematic variation of three major variables on the performance of computerized adaptive testing (CAT) procedures for the partial credit model. The three variables studied were the stopping rule for terminating the CATs, item pool size, and the distribution of the difficulty of the items in the pool. Results indicated that the standard error stopping rule performed better across the variety of CAT conditions than the minimum information stopping rule… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

2
37
0
1

Year Published

1996
1996
2018
2018

Publication Types

Select...
4
3

Relationship

1
6

Authors

Journals

citations
Cited by 32 publications
(40 citation statements)
references
References 9 publications
2
37
0
1
Order By: Relevance
“…Item pools with 30 to 60 items have been found adequate for successful CAT procedures with polytomous items (Dodd, Koch, & De Ayala, 1989; Dodd, Koch, & De Ayala, 1993). For the current study, two real pools of 28 and 95 items, respectively, served as models to generate small (30) and large (90) item pools.…”
Section: Methodsmentioning
confidence: 99%
See 2 more Smart Citations
“…Item pools with 30 to 60 items have been found adequate for successful CAT procedures with polytomous items (Dodd, Koch, & De Ayala, 1989; Dodd, Koch, & De Ayala, 1993). For the current study, two real pools of 28 and 95 items, respectively, served as models to generate small (30) and large (90) item pools.…”
Section: Methodsmentioning
confidence: 99%
“…Results indicated that the SE stopping rule yielded higher correlations between known and estimated abilities, while also producing considerably fewer floor/ceiling cases. Additionally, Dodd, Koch, and De Ayala (1993) found that, for adaptive test scored with the partial credit model, the SE stopping rule produced fewer floor/ceiling cases, while also resulting in shorter tests with greater measurement precision than the minimum information stopping rule.…”
mentioning
confidence: 98%
See 1 more Smart Citation
“…The administered tests for certain examinees may be undesirably lengthy or short because the required precision cannot be met or few items have improved the precision significantly. Under the unidimensional framework, some studies have been done on using different stopping rules in CAT (Dodd et al 1993), such as the minimum standard error (SE) stopping rule, the minimum information stopping rule (Dodd et al 1989), and the predicted standard error reduction (PSER) stopping rule (Choi et al 2011). Under the multidimensional framework, many previous studies on item selection methods were conducted in fixed-length MCATs (Mulder and van der Linden 2009;Su and Huang 2014;Wang et al 2011a, b;Yao 2011Yao , 2012.…”
Section: Background and Purposementioning
confidence: 99%
“…Interesting results were, for example, that compared to CAT with dichotomous item scores, the size of the item pool may be substantially smaller to get an accurate estimate of 0 (see e.g., De Ayala, 1993, and. Item pools should be not too small, however, in order to secure, for example, content validity.…”
Section: Polytomous Item Response Modelsmentioning
confidence: 99%