本文關(guān)鍵詞： 全功能極大似然估計(jì) 計(jì)算機(jī)化自適應(yīng)測(cè)驗(yàn) 項(xiàng)目反應(yīng)理論 在線標(biāo)定 題庫(kù)建設(shè)　出處：《心理學(xué)報(bào)》2016年09期 　論文類型：期刊論文

【摘要】：在線標(biāo)定技術(shù)由于具有諸多優(yōu)點(diǎn)而被廣泛應(yīng)用于計(jì)算機(jī)化自適應(yīng)測(cè)驗(yàn)(CAT)的新題標(biāo)定。Method A是想法最直接、算法最簡(jiǎn)單的CAT在線標(biāo)定方法,但它具有明顯的理論缺陷——在標(biāo)定過程中將能力估計(jì)值視為能力真值。將全功能極大似然估計(jì)方法(FFMLE)與"利用充分性結(jié)果"估計(jì)方法(ECSE)的誤差校正思路融入Method A(新方法分別記為FFMLE-Method A和ECSE-Method A),從理論上對(duì)能力估計(jì)誤差進(jìn)行校正,進(jìn)而克服Method A的標(biāo)定缺陷。模擬研究的結(jié)果表明:(1)在大多數(shù)實(shí)驗(yàn)條件下,兩種新方法較Method A總體上可以改進(jìn)標(biāo)定精度,且在測(cè)驗(yàn)長(zhǎng)度為10的短測(cè)驗(yàn)上的改進(jìn)幅度最大;(2)當(dāng)CAT測(cè)驗(yàn)長(zhǎng)度較短或中等(10或20題)時(shí),兩種新方法的表現(xiàn)與性能最優(yōu)的MEM已非常接近。當(dāng)測(cè)驗(yàn)長(zhǎng)度較長(zhǎng)(30題)時(shí),ECSE-Method A的總體表現(xiàn)最好、優(yōu)于MEM;(3)樣本量越大,各種方法的標(biāo)定精度越高。
[Abstract]:Because of its many advantages, online calibration technology has been widely used in the computerized adaptive test (CAT) of the new problem calibration. Method A is the most direct idea. The simplest on-line calibration method for CAT is proposed. However, it has obvious theoretical defects: in the process of calibration, the capability estimate is regarded as the true value of capability. The full function maximum likelihood estimation method (FFMLEE) and the "use of adequacy result" estimation method (. The method of error correction is integrated into Method A (the new method is called FFMLE-Method A and ECSE-Method A respectively). The error of capability estimation is corrected theoretically to overcome the calibration defect of Method A. the simulation results show that the error of capacity estimation is in most experimental conditions. Compared with Method A, the two new methods can improve the calibration accuracy, and have the largest improvement on the short test with the test length of 10. (2) when the length of CAT test is short or medium (10 or 20), the performance of the two new methods is very close to that of the MEM with the best performance, and when the length of the test is longer than 30 questions). The overall performance of ECSE-Method A is the best, which is better than that of ECSE-Method; The larger the sample size, the higher the calibration accuracy of various methods.
【作者單位】： 北京師范大學(xué)中國(guó)基礎(chǔ)教育質(zhì)量監(jiān)測(cè)協(xié)同創(chuàng)新中心;
【基金】：國(guó)家自然科學(xué)基金青年基金項(xiàng)目(31300862) 高等學(xué)校博士學(xué)科點(diǎn)專項(xiàng)科研基金項(xiàng)目新教師類(20130003120002) 東北師范大學(xué)應(yīng)用統(tǒng)計(jì)教育部重點(diǎn)實(shí)驗(yàn)室開放課題(KLAS 130028614)資助
【分類號(hào)】：B841
【正文快照】： 1引言量新的技能類型(如知識(shí)狀態(tài));(4)與多級(jí)項(xiàng)目反應(yīng)理論(Polytomous Item Response Theory,PIRT)結(jié)合在傳統(tǒng)紙筆測(cè)驗(yàn)(Paper-and-Pencil,PP)中,可以提供基于表現(xiàn)的題目類型(如開放題);(5)與多所有被試不論能力高低都作答相同的一批題目,所維IRT(Multidimensional IRT,MIRT)

【相似文獻(xiàn)】

相關(guān)期刊論文 前2條

1 陳平;辛濤;;認(rèn)知診斷計(jì)算機(jī)化自適應(yīng)測(cè)驗(yàn)中在線標(biāo)定方法的開發(fā)[J];心理學(xué)報(bào);2011年06期

2 ;[J];;年期

，

本文編號(hào)：1487114