The single-index panel data models with heterogeneous link function: mixture approach

Abstract

This paper investigates the data generating structure which can be represented as a mixture of single-index panel data model with heterogeneous link function. The switching between the states is governed by a hidden variable. We also offer an Expectation Maximization (EM) algorithm for estimating parameters numerically. The ability of the proposed mixture model will be illustrated with both the simulated performance and the empirical applications.

Keywords:

• Mixture models
• Single-index panel data
• Hidden variables
• Heterogeneous link function
• EM algorithm