HIGH-DIMENSIONAL EXPLORATORY ITEM FACTOR ANALYSIS BY A METROPOLIS-HASTINGS ROBBINS-MONRO ALGORITHM

被引：204
作者：
Cai, Li [1 ]
机构：
[1] Univ Calif Los Angeles, GSE & IS, Los Angeles, CA 90095 USA
来源：
VOX SANGUINIS | 2010年 / 98卷
基金：
美国国家科学基金会;
关键词：
stochastic approximation; SA; item response theory; IRT; Markov chain Monte Carlo; MCMC; numerical integration; categorical factor analysis; latent variable modeling; structural equation modeling; MAXIMUM-LIKELIHOOD-ESTIMATION; STOCHASTIC-APPROXIMATION ALGORITHM; LIMITED-INFORMATION; VARIABLE MODELS; INCOMPLETE DATA; LINEAR-MODELS; MARKOV-CHAINS; EM; FIT; IRT;
D O I：
10.1007/S11336-009-9136-X
中图分类号：
R5 [内科学];
学科分类号：
1002 ; 100201 ;
摘要：
A Metropolis-Hastings Robbins-Monro (MH-RM) algorithm for high-dimensional maximum marginal likelihood exploratory item factor analysis is proposed. The sequence of estimates from the MH-RM algorithm converges with probability one to the maximum likelihood solution. Details on the computer implementation of this algorithm are provided. The accuracy of the proposed algorithm is demonstrated with simulations. As an illustration, the proposed algorithm is applied to explore the factor structure underlying a new quality of life scale for children. It is shown that when the dimensionality is high, MH-RM has advantages over existing methods such as numerical quadrature based EM algorithm. Extensions of the algorithm to other modeling frameworks are discussed.
引用
收藏
页码：33 / 57
页数：25
相关论文
共 93 条
  • [1] BAYESIAN-ESTIMATION OF NORMAL OGIVE ITEM RESPONSE CURVES USING GIBBS SAMPLING
    ALBERT, JH
    [J]. JOURNAL OF EDUCATIONAL STATISTICS, 1992, 17 (03): : 251 - 269
  • [2] [Anonymous], 1997, Application of Mathematics
  • [3] [Anonymous], 2004, Explanatory item response models: A generalized linear and nonlinear approach
  • [4] [Anonymous], 2008, A Metropolis-Hastings Robbins-Monro algorithm for maximum likelihood nonlinear latent structure analysis with a comprehensive measurement model
  • [5] [Anonymous], 1969, PSYCHOMETRIC MONOGRA
  • [6] [Anonymous], ED PSYCHOL MEASUREME, DOI DOI 10.1177/0013164405282490
  • [7] [Anonymous], 1996, Markov chain Monte Carlo in practice
  • [8] [Anonymous], UC BERKELEY DIVISION
  • [9] [Anonymous], 2514 FRENCH NAT I RE
  • [10] *APT SYST INC, 2003, GAUSS VERS 6 08 COMP
12345678910