Applications and extensions of MCMC in IRT: Multiple item types, missing data, and rated responses
Applications and extensions of MCMC in IRT: Multiple item types, missing data, and rated responses
复制标题
DOI：
10.3102/10769986024004342
复制
发表时间：
1999-12-01
影响因子：
2.4
通讯作者：
Junker, BW
中科院分区：
文献类型：
--
作者：
Patz, RJ;Junker, BW
Patz and Junker（1999）基于大都会 - 杂货采样，《复杂项目响应理论》（IRT）设置中的远贝叶斯推论，描述了马尔可夫链蒙特卡洛（MCMC）策略。他们使用两参数logistic（2PL）模型演示了Rile基本方法。在本文中，我们将其基本的MCMC方法扩展到解决诸如无响应，设计遗失，多个评估者，猜测行为和部分信用（多态）休息等问题。我们将基本的MCMC方法应用于国家教育进度评估的两个示例1992年阅读中的试验评估：（a）多个项目格式（2PL，3PL和广义的部分信用）子测验，并具有缺失的响应数据； （b）使用称为广义线性逻辑测试模型（GLLTM）的新的IRT模型，一系列额定的二分短响应项。
Patz and Junker (1999) describe a general Markov chain Monte Carlo (MCMC) strategy, based on Metropolis-Hastings sampling, far Bayesian inference in complex item response theory (IRT) settings. They demonstrate rile basic methodology using the two-parameter logistic (2PL) model. In this paper we extend their basic MCMC methodology to address issues such as nonresponse, designed missingness, multiple raters, guessing behavior and partial credit (polytomous) rest items. We apply the basic MCMC methodology to two examples from the National Assessment of Educational Progress 1992 Trial State Assessment in Reading: (a) a multiple item format (2PL, 3PL, and generalized partial credit) subtest with missing response data; and (b) a sequence of rated, dichotomous short-response items, using a new IRT model called the generalized linear logistic test model (GLLTM).