10Semiparametric mixture regression models
10.1 Why semiparametric regression models?
Since the parametric model assumption, such as linearity might not be satisfied, both theoretically and practically, many semiparametric finite mixture of regressions (FMR) models have been proposed and demonstrated to have superior performance during the last few years. By allowing the mixing proportions to depend on a covariate, Young and Hunter (2010) and Huang and Yao (2012) studied semiparametric mixtures of regression models with varying proportions. Huang et al. (2013) and Xiang and Yao (2018) relaxed the parametric assumptions on the mean functions and/or variances to accommodate for complicated data structures. However, ...
Get Mixture Models now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
