東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

A comparison of two methods of polyt...

Thompson, Nathan A.

Linked to FindBook

Google Book

Amazon

博客來

A comparison of two methods of polytomous computerized classification testing for multiple cutscores.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	A comparison of two methods of polytomous computerized classification testing for multiple cutscores./
Author:	Thompson, Nathan A.
Description:	123 p.
Notes:	Adviser: David J. Weiss.
Contained By:	Dissertation Abstracts International68-07B.
Subject:	Psychology, Psychometrics. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3273166
ISBN:	9780549116714

A comparison of two methods of polytomous computerized classification testing for multiple cutscores.
Thompson, Nathan A.

A comparison of two methods of polytomous computerized classification testing for multiple cutscores. - 123 p.

Adviser: David J. Weiss.

Thesis (Ph.D.)--University of Minnesota, 2007.

The sequential probability ratio test (SPRT: Wald, 1947) and adaptive mastery testing (AMT: Kingsbury & Weiss, 1983) have been shown to be effective termination criteria for computerized classification testing (CCT: Kingsbury & Weiss, 1983; Reckase, 1983; Spray & Reckase, 1994; Lin & Spray, 2000). The SPRT and AMT were originally designed for only two classifications, such as "pass" and "fail" (Kingsbury & Weiss, 1983), but can be expanded to three or more classifications (Weiss & Kingsbury, 1984; Spray, 1993; Eggen & Straetmans, 2000). However, all research that has been done with the multiple cutscore CCT has utilized only dichotomous item response theory models. A procedure has been proposed (Lau & Wang, 1998; 1999; 2000) to modify the SPRT to accommodate ordered polytomous IRT models such as the partial credit model (Masters, 1982) and the generalized partial credit model (Muraki, 1992). These models potentially increase the level of information provided by an item across the ability scale, which is increasingly important as the number of classifications increases. This study investigated the applicability of polytomous item response theory methods to CCT for multiple cutscores. The relative efficiency of the procedure as compared to the dichotomous multiple cutscore CCT, as well as a comparison of termination criteria and item selection criteria, was investigated in a nionte carlo simulation study. It was found that the advantages of testing efficiency, evaluated by the average test length and percentage of correct classifications, for two-classification CCT are even greater for three-classification CCT. CCTs with the SPRT termination criterion utilized fewer items than AMT while being matched on observed accuracy.

ISBN: 9780549116714Subjects--Topical Terms:

1017742
Psychology, Psychometrics.

A comparison of two methods of polytomous computerized classification testing for multiple cutscores.
LDR:02633nam 2200265 a 45 001 962607
005 20110830
008 110831s2007 ||||||||||||||||| ||eng d
020 $a 9780549116714
035 $a (UMI)AAI3273166
035 $a AAI3273166
040 $a UMI $c UMI
100 1 $a Thompson, Nathan A. $3 1285667
245 1 2 $a A comparison of two methods of polytomous computerized classification testing for multiple cutscores.
300 $a 123 p.
500 $a Adviser: David J. Weiss.
500 $a Source: Dissertation Abstracts International, Volume: 68-07, Section: B, page: 4884.
502 $a Thesis (Ph.D.)--University of Minnesota, 2007.
520 $a The sequential probability ratio test (SPRT: Wald, 1947) and adaptive mastery testing (AMT: Kingsbury & Weiss, 1983) have been shown to be effective termination criteria for computerized classification testing (CCT: Kingsbury & Weiss, 1983; Reckase, 1983; Spray & Reckase, 1994; Lin & Spray, 2000). The SPRT and AMT were originally designed for only two classifications, such as "pass" and "fail" (Kingsbury & Weiss, 1983), but can be expanded to three or more classifications (Weiss & Kingsbury, 1984; Spray, 1993; Eggen & Straetmans, 2000). However, all research that has been done with the multiple cutscore CCT has utilized only dichotomous item response theory models. A procedure has been proposed (Lau & Wang, 1998; 1999; 2000) to modify the SPRT to accommodate ordered polytomous IRT models such as the partial credit model (Masters, 1982) and the generalized partial credit model (Muraki, 1992). These models potentially increase the level of information provided by an item across the ability scale, which is increasingly important as the number of classifications increases. This study investigated the applicability of polytomous item response theory methods to CCT for multiple cutscores. The relative efficiency of the procedure as compared to the dichotomous multiple cutscore CCT, as well as a comparison of termination criteria and item selection criteria, was investigated in a nionte carlo simulation study. It was found that the advantages of testing efficiency, evaluated by the average test length and percentage of correct classifications, for two-classification CCT are even greater for three-classification CCT. CCTs with the SPRT termination criterion utilized fewer items than AMT while being matched on observed accuracy.
590 $a School code: 0130.
650 4 $a Psychology, Psychometrics. $3 1017742
690 $a 0632
710 2 $a University of Minnesota. $3 676231
773 0 $t Dissertation Abstracts International $g 68-07B.
790 $a 0130
790 1 0 $a Weiss, David J., $e advisor
791 $a Ph.D.
792 $a 2007
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3273166