Partial identifiability of restricted latent class models
From MaRDI portal
Publication:2215726
Abstract: Latent class models have wide applications in social and biological sciences. In many applications, pre-specified restrictions are imposed on the parameter space of latent class models, through a design matrix, to reflect practitioners' assumptions about how the observed responses depend on subjects' latent traits. Though widely used in various fields, such restricted latent class models suffer from non-identifiability due to their discreteness nature and complex structure of restrictions. This work addresses the fundamental identifiability issue of restricted latent class models by developing a general framework for strict and partial identifiability of the model parameters. Under correct model specification, the developed identifiability conditions only depend on the design matrix and are easily checkable, which provide useful practical guidelines for designing statistically valid diagnostic tests. Furthermore, the new theoretical framework is applied to establish, for the first time, identifiability of several designs from cognitive diagnosis applications.
Recommendations
- Identifiability of restricted latent class models with binary responses
- Identifiability of latent class models with covariates
- Identifying Latent Structures in Restricted Latent Class Models
- A note on weaker conditions for identifying restricted latent class models for binary responses
- Identifiability of extended latent class models with individual covariates
Cites work
- A sequential cognitive diagnosis model for polytomous responses
- An application of classical invariant theory to identifiability in nonparametric mixtures.
- Asymptotic Statistics
- Bayesian estimation of the DINA \(Q\) matrix
- Cluster analysis for cognitive diagnosis: theory and applications
- Deep learning
- Defining a family of cognitive diagnosis models using log-linear models with latent variables
- Efficient estimation and local identification in latent class analysis
- Estimating multiple classification latent class models
- Exploratory latent structure analysis using both identifiable and unidentifiable models
- Hierarchical diagnostic classification models morphing into unidimensional `diagnostic' classification models -- a commentary
- Hierarchical diagnostic classification models: a family of models for estimating and testing attribute hierarchies
- Higher-order latent trait models for cognitive diagnosis
- scientific article; zbMATH DE number 1817585 (Why is no real title available?)
- scientific article; zbMATH DE number 46578 (Why is no real title available?)
- Identifiability of diagnostic classification models
- Identifiability of Mixtures of Product Measures
- Identifiability of parameters in latent structure models with many observed variables
- Identifiability of restricted latent class models with binary responses
- Identifying Latent Structures in Restricted Latent Class Models
- Non-uniqueness in probabilistic numerical identification of bacteria
- Statistical analysis of Q-matrix based diagnostic classification models
- The DINA model as a constrained general diagnostic model: two variants of a model equivalency
- The generalized DINA model framework
- The sufficient and necessary condition for the identifiability and estimability of the DINA Model
Cited in
(36)- Identifiability of extended latent class models with individual covariates
- Identifiability of restricted latent class models with binary responses
- Partial identification of latent correlations with binary data
- A unified theory of the completeness of Q-matrices for the DINA model
- Exploratory restricted latent class models with monotonicity requirements under Pòlya-gamma data augmentation
- Learning large \(Q\)-matrix by restricted Boltzmann machines
- Identifiability of latent class models with covariates
- Direct estimation of diagnostic classification model attribute mastery profiles via a collapsed Gibbs sampling algorithm
- Diagnostic classification analysis of problem-solving competence using process data: an item expansion method
- Half-trek criterion for identifiability of latent variable models
- A Gibbs sampling algorithm with monotonicity constraints for diagnostic classification models
- Partial-mastery cognitive diagnosis models
- Hypothesis testing of the \(Q\)-matrix
- Identifying Latent Structures in Restricted Latent Class Models
- Sufficient and necessary conditions for the identifiability of the Q-matrix
- Identification of latent class Markov models with multiple indicators and correlated measurement errors
- Structured latent factor analysis for large-scale data: identifiability, estimability, and their implications
- Constrained latent class models: Some further applications†
- Identifiability of Hierarchical Latent Attribute Models
- A Joint MLE Approach to Large-Scale Structured Latent Attribute Analysis
- Complete Q‐matrices in conjunctive models on general attribute structures
- Bridging parametric and nonparametric methods in cognitive diagnosis
- Generic identifiability of the DINA model and blessing of latent dependence
- A note on weaker conditions for identifying restricted latent class models for binary responses
- Going deep in diagnostic modeling: deep cognitive diagnostic models (DeepCDMs)
- Diagnostic classification models for testlets: methods and theory
- Statistical inference for covariate-adjusted and interpretable generalized latent factor model with application to testing fairness
- Deep generative modeling for cognitive diagnosis via exploratory DeepCDMs
- A general diagnostic modelling framework for forced-choice assessments
- Teamwork cognitive diagnostic modeling
- Generalized latent variable models for location, scale, and shape parameters
- The BLIM, the DINA, and their polytomous extensions. Rejoinder to the commentary by Chiu, Köhn, and Ma
- Item response theory -- a statistical framework for educational and psychological measurement
- Sufficient and necessary conditions for the identifiability of DINA models with polytomous responses
- New paradigm of identifiable general-response cognitive diagnostic models: beyond categorical data
- New directions in algebraic statistics: three challenges from 2023
This page was built for publication: Partial identifiability of restricted latent class models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2215726)
