Two algorithms for fitting constrained marginal models.

Journal article

The two main algorithms that have been considered for fitting constrained marginal models to discrete data, one based on Lagrange multipliers and the other on a regression model, are studied in detail. It is shown that the updates produced by the two methods are identical, but that the Lagrangian method is more efficient in the case of identically distributed observations. A generalization is given of the regression algorithm for modelling the effect of exogenous individual-level covariates, a context in which the use of the Lagrangian algorithm would be infeasible for even moderate sample sizes. An extension of the method to likelihood-based estimation under L 1-penalties is also considered.

Authors: Evans, R; Forcina, A

• Publication status: Published
• Journal: Computational statistics and data analysis
• Volume: 66
• Pages: 1-7
• Publication date: 2013-10-01
• DOI: 10.1016/j.csda.2013.02.001
• ISSN: 0167-9473
• Language: English
• Keywords: maximum likelihood; categorical data; non-linear constraint; L1-penalty; marginal log-linear model