東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

The Mantel-Haenszel procedure for DI...

Monahan, Patrick O'Neal.

FindBook

Google Book

Amazon

博客來

The Mantel-Haenszel procedure for DIF: Alternative matching scores to control type I error and improve distributional properties.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	The Mantel-Haenszel procedure for DIF: Alternative matching scores to control type I error and improve distributional properties./
作者:	Monahan, Patrick O'Neal.
面頁冊數:	393 p.
附註:	Source: Dissertation Abstracts International, Volume: 63-04, Section: A, page: 1313.
Contained By:	Dissertation Abstracts International63-04A.
標題:	Education, Tests and Measurements. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3050828
ISBN:	0493654690

The Mantel-Haenszel procedure for DIF: Alternative matching scores to control type I error and improve distributional properties.
Monahan, Patrick O'Neal.

The Mantel-Haenszel procedure for DIF: Alternative matching scores to control type I error and improve distributional properties. - 393 p.

Source: Dissertation Abstracts International, Volume: 63-04, Section: A, page: 1313.

Thesis (Ph.D.)--The University of Iowa, 2002.

The Mantel-Haenszel (MH) procedure is a nonparametric, contingency-table, method, commonly used in psychometrics for detecting differential item functioning (DIF). In the MH procedure for DIF, the conditional association between group (Reference and Focal) and dichotomous item score is estimated and tested, after controlling for overall performance of examinees. The control (matching) variable is usually the total number of items answered correctly (number-correct score). Therefore, the matching variable in the MH procedure for DIF: (a) consists of correlated categories, and (b) contains measurement error as a fallible surrogate for latent proficiency. If dichotomous item scores conform to item response theory (IRT) models more complex than the Rasch model, and number-correct score is the matching variable in the MH procedure for DIF, inflation of Type I error of the <math> <f> <g>c</g>2<inf>MH</inf></f> </math> test and inflation of null-DIF bias of the MH odds ratio (<math> <f> <a><ac><g>D</g></ac><ac>&d4;</ac></a><inf>MH</inf></f> </math> is log transformation of odds ratio) may occur.

ISBN: 0493654690Subjects--Topical Terms:

1017589
Education, Tests and Measurements.

The Mantel-Haenszel procedure for DIF: Alternative matching scores to control type I error and improve distributional properties.
LDR:03579nam 2200301 a 45 001 930418
005 20110429
008 110429s2002 eng d
020 $a 0493654690
035 $a (UnM)AAI3050828
035 $a AAI3050828
040 $a UnM $c UnM
100 1 $a Monahan, Patrick O'Neal. $3 1253980
245 1 0 $a The Mantel-Haenszel procedure for DIF: Alternative matching scores to control type I error and improve distributional properties.
300 $a 393 p.
500 $a Source: Dissertation Abstracts International, Volume: 63-04, Section: A, page: 1313.
500 $a Supervisor: Robert D. Ankenmann.
502 $a Thesis (Ph.D.)--The University of Iowa, 2002.
520 $a The Mantel-Haenszel (MH) procedure is a nonparametric, contingency-table, method, commonly used in psychometrics for detecting differential item functioning (DIF). In the MH procedure for DIF, the conditional association between group (Reference and Focal) and dichotomous item score is estimated and tested, after controlling for overall performance of examinees. The control (matching) variable is usually the total number of items answered correctly (number-correct score). Therefore, the matching variable in the MH procedure for DIF: (a) consists of correlated categories, and (b) contains measurement error as a fallible surrogate for latent proficiency. If dichotomous item scores conform to item response theory (IRT) models more complex than the Rasch model, and number-correct score is the matching variable in the MH procedure for DIF, inflation of Type I error of the <math> <f> <g>c</g>2<inf>MH</inf></f> </math> test and inflation of null-DIF bias of the MH odds ratio (<math> <f> <a><ac><g>D</g></ac><ac>&d4;</ac></a><inf>MH</inf></f> </math> is log transformation of odds ratio) may occur.
520 $a The primary purpose of this study was to investigate whether eight alternative matching scores control null-DIF empirical distributional properties of the MH procedure better than number-correct score. Investigations regarding MH, DIF, and Type I error have simulated data only with IRT models. In the present study, data were simulated with both the three-parameter logistic (3PL) IRT model, and a non-IRT technique involving the four-parameter beta compound binomial model for specifying the true score distribution.
520 $a Number-correct score displayed inflation in both types of simulated data. Four alternative matching scores consistently controlled the null-DIF bias of <math> <f> <a><ac><g>D</g></ac><ac>&d4;</ac></a><inf>MH</inf></f> </math> and the mean and SD of the empirical <math> <f> <g>c</g>2<inf>MH</inf></f> </math> distribution better than number-correct score: (a) categories of the estimated IRT proficiency parameter (<math> <f> <a><ac><g>q</g></ac><ac>&d4;</ac></a></f> </math>); (b) categories of the sum of weighted item scores, where the weights were either classical item-total biserial correlations or factor loadings from the first common factor of a factor analysis of tetrachoric correlations; and (c) Kelley's regressed true score estimates. However, the Kelley score performed worst of all matching scores with regard to empirical standard error of <math> <f> <a><ac><g>D</g></ac><ac>&d4;</ac></a><inf>MH</inf></f> </math>.
590 $a School code: 0096.
650 4 $a Education, Tests and Measurements. $3 1017589
650 4 $a Psychology, Psychometrics. $3 1017742
690 $a 0288
690 $a 0632
710 2 0 $a The University of Iowa. $3 1017439
773 0 $t Dissertation Abstracts International $g 63-04A.
790 $a 0096
790 1 0 $a Ankenmann, Robert D., $e advisor
791 $a Ph.D.
792 $a 2002
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3050828