Multiple correspondence analysis and the multilogit bilinear model
From MaRDI portal
Publication:2397131
Abstract: Multiple Correspondence Analysis (MCA) is a dimension reduction method which plays a large role in the analysis of tables with categorical nominal variables such as survey data. Though it is usually motivated and derived using geometric considerations, in fact we prove that it amounts to a single proximal Newtown step of a natural bilinear exponential family model for categorical data the multinomial logit bilinear model. We compare and contrast the behavior of MCA with that of the model on simulations and discuss new insights on the properties of both exploratory multivariate methods and their cognate models. One main conclusion is that we could recommend to approximate the multilogit model parameters using MCA. Indeed, estimating the parameters of the model is not a trivial task whereas MCA has the great advantage of being easily solved by singular value decomposition and scalable to large data.
Recommendations
Cites work
- A Combined Approach to Contingency Table Analysis Using Correspondence Analysis and Log-Linear Analysis
- A generalized least-square matrix decomposition
- A new model for visualizing interactions in analysis of variance
- An analysis and synthesis of multiple correspondence analysis, optimal scaling, dual scaling, homogeneity analysis and other methods for quantifying categorical multivariate data
- Correspondence analysis and related methods in practice
- Correspondence Analysis in Practice
- Correspondence analysis used complementary to loglinear analysis
- Generalised bilinear regression
- Generalized bilinear models
- Generalized latent trait models
- Generalized low rank models
- Graphical representations and odds ratios in a distance-association model for the analysis of cross-classified data
- Handling missing values with regularized iterative multiple correspondence analysis
- Horseshoes in multidimensional scaling and local kernel methods
- scientific article; zbMATH DE number 982488 (Why is no real title available?)
- scientific article; zbMATH DE number 4199329 (Why is no real title available?)
- scientific article; zbMATH DE number 4076355 (Why is no real title available?)
- scientific article; zbMATH DE number 3766832 (Why is no real title available?)
- scientific article; zbMATH DE number 3782181 (Why is no real title available?)
- scientific article; zbMATH DE number 47310 (Why is no real title available?)
- scientific article; zbMATH DE number 3466361 (Why is no real title available?)
- scientific article; zbMATH DE number 3610609 (Why is no real title available?)
- scientific article; zbMATH DE number 1063647 (Why is no real title available?)
- scientific article; zbMATH DE number 6107964 (Why is no real title available?)
- scientific article; zbMATH DE number 749308 (Why is no real title available?)
- scientific article; zbMATH DE number 1931821 (Why is no real title available?)
- scientific article; zbMATH DE number 952764 (Why is no real title available?)
- scientific article; zbMATH DE number 918093 (Why is no real title available?)
- scientific article; zbMATH DE number 3290846 (Why is no real title available?)
- Latent variable models and factor analysis. A unified approach
- Logistic biplots
- MIMCA: multiple imputation for categorical variables with multiple correspondence analysis
- Model Selection and Validation for Yield Trials with Interaction
- Multiple correspondence analysis.
- Multiple factor analysis by example using R
- Multiplicative Interaction in Generalized Linear Models
- Ordinal Association in Contingency Tables: Some Interpretive Aspects
- Partitioning of interaction in analysis of variance
- Poisson noise reduction with non-local PCA
- Principal component analysis of binary data by iterated singular value decomposition
- Regularized multiple correspondence analysis
- Simple structure in component analysis techniques for mixtures of qualitative and quantitative variables
- The analysis of cross-classified data having ordered and/or unordered categories: Association models, correlation models, and asymmetry models for contingency tables with or without missing entries
- The Gifi system of descriptive multivariate analysis.
Cited in
(14)- Multiple imputation: a review of practical and theoretical findings
- Diagnostics in a simple correspondence analysis model: an approach based on Cook's distance for log-linear models
- Low-rank model with covariates for count data with missing values
- Logistic biplot for nominal data
- Low-dimensional tracking of association structures in categorical data
- scientific article; zbMATH DE number 4199329 (Why is no real title available?)
- scientific article; zbMATH DE number 4041121 (Why is no real title available?)
- scientific article; zbMATH DE number 2138431 (Why is no real title available?)
- Regularized multiple correspondence analysis
- Correspondence analysis and classification
- Variants of non-symmetric correspondence analysis for nominal and ordinal variables
- An efficient algorithm for joint correspondence analysis
- Alternative bootstrap confidence regions for multiple correspondence analysis
- Online optimal adaptive output and state feedback controllers design for partially unknown continuous bilinear systems based on policy iteration
This page was built for publication: Multiple correspondence analysis and the multilogit bilinear model
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2397131)
