Scalable Bayesian approach for the DINA Q-matrix estimation combining stochastic optimization and variational inference

DOI10.1007/S11336-022-09884-4zbMath1514.62308arXiv2105.09495WikidataQ114222774 ScholiaQ114222774MaRDI QIDQ6160329

Kensuke Okada, Motonori Oka

Publication date: 23 June 2023

Published in: Psychometrika (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2105.09495

zbMATH Keywords

stochastic optimizationvariational inferencediagnostic classification modelsdeterministic inputs noisy ``and gate (DINA) modelQ-matrix estimation

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Bayesian inference (62F15) Stochastic approximation (62L20) Applications of statistics to psychology (62P15)

Related Items (1)

Dynamical non-compensatory multidimensional IRT model using variational approximation

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Identifiability of diagnostic classification models
• Fitting an item response theory model with random item effects across groups by a variational approximation method
• The generalized DINA model framework
• High-dimensional exploratory item factor analysis by a Metropolis-Hastings Robbins-Monro algorithm
• Defining a family of cognitive diagnosis models using log-linear models with latent variables
• Cluster analysis for cognitive diagnosis: theory and applications
• Bayesian estimation of the DINA \(Q\) matrix
• A variational maximization-maximization algorithm for generalized linear mixed models with crossed random effects
• Convergence of a stochastic approximation version of the EM algorithm
• Identifiability of restricted latent class models with binary responses
• Variational Bayes inference algorithm for the saturated diagnostic classification model
• Computation for latent variable model estimation: a unified stochastic proximal framework
• A Gibbs sampling algorithm that estimates the \(Q\)-matrix for the DINA model
• An exploratory diagnostic model for ordinal responses with binary attributes: identifiability and estimation
• A sparse latent class model for cognitive diagnosis
• A constrained Metropolis-Hastings Robbins-Monro algorithm for \(\boldsymbol{Q}\) matrix estimation in DINA models
• Variational approximations for categorical causal modeling with latent variables
• Higher-order latent trait models for cognitive diagnosis
• On the identifiability of diagnostic classification models
• Estimating the cognitive diagnosis \(Q\) matrix with expert knowledge: application to the fraction-subtraction dataset
• The sufficient and necessary condition for the identifiability and estimability of the DINA Model
• Theory of self-learning \(Q\)-matrix
• Hierarchical diagnostic classification models: a family of models for estimating and testing attribute hierarchies
• Julia: A Fresh Approach to Numerical Computing
• Data Analytic Methods for Latent Partially Ordered Classification Models
• Acceleration of Stochastic Approximation by Averaging
• Introduction to Stochastic Search and Optimization
• Identifying Latent Structures in Restricted Latent Class Models
• 10.1162/jmlr.2003.3.4-5.993
• Statistical Analysis ofQ-Matrix Based Diagnostic Classification Models
• A Stochastic Approximation Method
• A Joint MLE Approach to Large-Scale Structured Latent Attribute Analysis

This page was built for publication: Scalable Bayesian approach for the DINA Q-matrix estimation combining stochastic optimization and variational inference