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

An investigation of content- and con...

Deville, Craig W.

Linked to FindBook

Google Book

Amazon

博客來

An investigation of content- and construct-related evidence of self-assessment items using multidimensional scaling.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	An investigation of content- and construct-related evidence of self-assessment items using multidimensional scaling./
Author:	Deville, Craig W.
Description:	184 p.
Notes:	Source: Dissertation Abstracts International, Volume: 55-03, Section: A, page: 5390.
Contained By:	Dissertation Abstracts International55-03A.
Subject:	Education, Tests and Measurements. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=9420943

An investigation of content- and construct-related evidence of self-assessment items using multidimensional scaling.
Deville, Craig W.

An investigation of content- and construct-related evidence of self-assessment items using multidimensional scaling. - 184 p.

Source: Dissertation Abstracts International, Volume: 55-03, Section: A, page: 5390.

Thesis (Ph.D.)--The Ohio State University, 1994.

The purpose of this study was to investigate the value, feasibility, and interpretability of an innovative empirical validation technique that combines content- and construct-related evidence. The review of literature demonstrates that the concept behind the empirical technique has been called for by numerous measurement specialists since the 1940's. A controversy in the field developed in the 1970's when several people argued that content validity was not validity at all since it typically dealt with ratings given by experts to questions regarding content during the phase of instrument development, and did not concern itself with actual responses to the instrument. What was needed was a methodology that systematically compared evidence provided by content area experts with evidence from actual responses to the instrument.Subjects--Topical Terms:

1017589
Education, Tests and Measurements.

An investigation of content- and construct-related evidence of self-assessment items using multidimensional scaling.
LDR:03358nam a2200313 4500 001 1966378
005 20141125142152.5
008 150210s1994 ||||||||||||||||| ||eng d
035 $a (MiAaPQ)AAI9420943
035 $a AAI9420943
040 $a MiAaPQ $c MiAaPQ
100 1 $a Deville, Craig W. $3 2103193
245 1 3 $a An investigation of content- and construct-related evidence of self-assessment items using multidimensional scaling.
300 $a 184 p.
500 $a Source: Dissertation Abstracts International, Volume: 55-03, Section: A, page: 5390.
500 $a Adviser: William E. Loadman.
502 $a Thesis (Ph.D.)--The Ohio State University, 1994.
520 $a The purpose of this study was to investigate the value, feasibility, and interpretability of an innovative empirical validation technique that combines content- and construct-related evidence. The review of literature demonstrates that the concept behind the empirical technique has been called for by numerous measurement specialists since the 1940's. A controversy in the field developed in the 1970's when several people argued that content validity was not validity at all since it typically dealt with ratings given by experts to questions regarding content during the phase of instrument development, and did not concern itself with actual responses to the instrument. What was needed was a methodology that systematically compared evidence provided by content area experts with evidence from actual responses to the instrument.
520 $a The present study utilized a foreign language self-assessment placement instrument, which consisted of 32 "can do" items placed on a five-point Likert scale. The test blueprint specified that the items represent the four traditional skill areas: Speaking, Listening, Reading, and Writing. The instrument was administered to 1449 students enrolled in the 101-103 language courses in the French, German, and Spanish departments at the Ohio State University during the Autumn Quarter, 1992.
520 $a Four subject matter experts were asked to provide item similarity/dissimilarity judgments on a nine-point scale for all paired comparisons of the items. Judges could use whatever criteria they thought appropriate to give their ratings.
520 $a The data from the students and the experts were examined separately using multidimensional scaling followed by cluster and discriminant analyses. The structure of the data underlying both the student and rater scaling solutions corresponded closely to that specified in the test blueprint. In addition, using canonical correlation, a comparison of the two scaling solutions revealed remarkable similarity in the two solutions. Finally, results from replicated multidimensional scaling showed that the structure of the student solution was quite stable across different student ability levels and language backgrounds.
520 $a The study demonstrated the value of the empirical technique in comparing data from content experts and test respondents. Content validity can be tied to actual response data, thus providing a stronger argument for validity.
590 $a School code: 0168.
650 4 $a Education, Tests and Measurements. $3 1017589
650 4 $a Psychology, Psychometrics. $3 1017742
690 $a 0288
690 $a 0632
710 2 $a The Ohio State University. $3 718944
773 0 $t Dissertation Abstracts International $g 55-03A.
790 $a 0168
791 $a Ph.D.
792 $a 1994
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=9420943