A Divided Latent Class analysis for Big Data

Statistical methods are a fundamental component in the big data environment. Among these methods: Latent class analysis (LCA), which is a subset of structural equation modeling, used to create classes in the case of multivariate categorical data. The use of this method to analyze massive data sets represents an expensive computational task. In this paper, we propose a Divide-and-Conquer approach for LCA model, the aim is to estimate the LCA parameters when this method is used for massive data sets. The performance of our approach will be verified by carrying out a numerical simulation.