我们的网站为什么显示成这样?

可能因为您的浏览器不支持样式,您可以更新您的浏览器到最新版本,以获取对此功能的支持,访问下面的网站,获取关于浏览器的信息:

|本期目录/Table of Contents|

 四参数Logistic模型研究进展及其评析(PDF)

《心理学探新》[ISSN:1003-5184/CN:36-1228/B]

期数:
 2010年30卷03期
页码:
 69-73
栏目:
 心理统计与测量
出版日期:
 2010-05-01

文章信息/Info

Title:
 The Advances of Four-Parameter Logistic Model and Its Comments
作者:
 简小珠12张敏强1彭春妹2
 1.华南师范大学 心理应用研究中心,广州 510631;2.井冈山大学 教育学院,吉安 343009
Author(s):
 Jian Xiaozhu12Zhang Minqiang1Peng Chunmei2
 1.Center for Psychological Application,South China Normal University,Guangzhou 510631; 2.Education School,Jinggangshan University,Ji’an 343009
关键词:
 IRT四参数模型猜测现象睡眠现象
Keywords:
 IRTFour-Parameter Logistic Modelguessingsleeping
分类号:
 B841.2
DOI:
 -
文献标识码:
 A
摘要:
 在测验中存在着低能力被试答对高难度试题的猜测现象,和高能力被试答错容易试题的睡眠现象,此时可以使用四参数模型来分析测验数据。Barton和Lord认为应用四参数模型的实践意义不大,但结论的依据不充分。近年来研究者从测验项目拟合,改善被试能力估计等方面进行了分析,认为在四参数模型下可以有效纠正被试能力高估或低估现象,认为单、两、三参数模型是四参数模型的特例,建议使用四参数模型。
Abstract:
 In the paper-pencil test and CAT,there exist the phenomena that the high-ability examinee makes wrong response on the easy item(guessing),and that the low-ability examinee makes correct response on the difficult item(sleeping).Many researches have been made on the topic of the guessing or ceiling phenomenon under four-parameter Logistic model(4PM).Barton & Lord didn’t agree to urge the use of 4PM.In recent years,however,many researchers have made the researches and proposed the use of 4PM.It has been demonstrated that:(1)4PM can improve the good-fitness of mode-data;(2)4PM can rectify the underestimation phenomenon when there exist the sleeping phenomenon,and 4PM can rectify the overestimation phenomenon when there exist the guessing phenomenon;(3)one-parameter,two-parameter and three-parameter Logistic model are the special case of 4PM.The new program WINSTEPS has published.The user can estimate the item parameter under 4PM using the WINSTEPS.WINSTEPS will help to popularize the 4PM.

参考文献/References

 1Wright B D.Solving measurement problems with the research model.Journal of Educational Measurement,1977,14:97-116.
2Reise S P,Waller N G.How many IRT parameters does it take to model psychopathology items?Psychological Methods,2003,8(2):164-184.
3简小珠,戴海崎,彭春妹.IRT中Logistic模型的c、γ参数对能力估计的改善.心理学报,2007,39(4):737-746.
4简小珠.Logistic模型c、γ参数对被试作答的拟合能力.硕士论文.南昌:江西师范大学,2006.
5Hessen D J.A new class of parametric IRT models for dichotomous item scores.Journal of Applied Measurement,2004,5(4):385-397.
6McDonald R P.Non-linear factor analysis.Psychometric Monographs,1967:15.
7Barton M A,Lord F M.An upper asymptote for the three-parameter Logistic item response model.In:Research Bulletin.Princeton,NJ:Educational Testing Service,1981:81-20.
8Hambleton R K,Swaminathan H.Item response theory:Principles and applications.Boston:Kluwer-Nijhoff,1985:48-49.
9漆书青,戴海崎.项目反应理论及其应用研究.南昌:江西高校出版社,1992.
10Embretson S E,Reise S P.Item response theory for psychologists.Mahwah:Lawrence Erlbaum Associates,Inc,2000.
11Baker F B.Item response theory:parameter estimation techniques.2nd eds.New York:Marcel Dekker,nc.2004.
12漆书青,戴海崎,丁树良.现代教育与心理测量学原理.北京:高等教育出版社,2002.
13Hessen D J.Constant latent odds-ratios models and the Mantel-Haenszel null hypothesis.Psychometrika,2005,70(3):497-516.
14戴海崎,简小珠.被试作答的偶然性对IRT能力估计的影响研究.心理科学,2005,28(6):1433-1436.
15Rulison K,Loken E.I've fallen and I can't get up:Can high-ability students recover from early mistakes in CAT?Applied Psychological Measurement,2009,33(2):83-101.
16〖JP2〗Linacre J M.A user's guide to winsteps ministep rasch-model computer programs.Retrieved from:http://199.236.93.8/winman/index.htm?asymptote.htm.2009-6-28.
17吴德福.四参数Logistic函数的简化求解.中华核医学杂志,1990,10(1):48-50.
18Edwards P S.The who immunoassay program,Version 5.2.London:Middlesex Hospital,1985.
19Brendan.Retrieved from:http://www.brendan.com/5pl.html.2009-7-03

备注/Memo

备注/Memo:
 基金项目:教育部省部共建人文社会科学重点研究基地项目(2009JJDXLX006),广东省自然科学基金项目(9151063101000002),江西省社会科学规划“十一五”学科共建项目(09JY226)。 通讯作者:张敏强,E-mail:zhangmq1117@yahoo.com.cn。
更新日期/Last Update:  2011-11-03