USING THE MIXED MODEL APPROACH FOR CLASSIFICATION PURPOSES

by Yıldız ATEŞ

In a mixture model, the data set may not belong to a single population. In other words, the data set may be a heterogeneous data set from multiple populations. Mixed models are used for both continuous and discrete data. Furthermore, mixture modeling can be used for both classification and regression purposes. Mixed regression is widely applied when the dependent variable has a binomial, Poisson, or normal distribution.

ISBN: 978-625-378-062-3