Introduction
Introduction Statistics Contact Development Disclaimer Help
ERIC ED284901: The Use of Unidimensional Item Parameter Estimates o...
by ERIC
Thumbnail
Download
Web page
The purpose of this study was to investigate the effect
of using multidimensional items in a computer adaptive
test (CAT) setting which assumes a unidimensional item
response theory (IRT) framework. Previous research has
suggested that the composite of multidimensional
abilities being estimated by a unidimensional IRT model
is not constant throughout the entire unidimensional
ability scale. Results of this study suggest that
univariate calibration of multidimensional data tends to
"filter" out the multidimensionality. The closer an
item's multidimensional composite aligns itself with the
calibrated univariate ability scale's orientation, the
larger the estimated discrimination parameter. If CAT
item selection is based upon the amount of information an
item provides, items requiring similar (theta sub 1,
theta sub 2) will most often be selected. These results
further imply that in a CAT different abilities
throughout the theta sub 1, theta sub 2 plane could
receive sets of items that discriminate between theta sub
1 and theta sub 2 to different degrees. Also, different
abilities along the mapped univariate scale could receive
tests having different proportions of item content. A
description of the ACT Mathematics Usage Test is
appended. (Author/JAZ)
Date Published: 2014-12-25 22:48:40
Identifier: ERIC_ED284901
Item Size: 32328663
Language: english
Media Type: texts
# Topics
ERIC Archive; Adaptive Testing; Colle...
# Collections
ericarchive
additional_collections
# Uploaded by
@chris85
# Similar Items
View similar items
PHAROS
You are viewing proxied material from tilde.pink. The copyright of proxied material belongs to its original authors. Any comments or complaints in relation to proxied material should be directed to the original authors of the content concerned. Please see the disclaimer for more details.