scholarly journals Unsupervised learning of mixture regression models for longitudinal data

2018 ◽  
Vol 125 ◽  
pp. 44-56 ◽  
Author(s):  
Peirong Xu ◽  
Heng Peng ◽  
Tao Huang
Keyword(s):  
Longitudinal Data ◽  
Unsupervised Learning ◽  
Regression Models ◽  
Mixture Regression ◽  
Mixture Regression Models

scholarly journals Modelling semi-continuous data using mixture regression models with an application to cattle production yields

2011 ◽  
Vol 150 (1) ◽  
pp. 109-121 ◽  
Author(s):  
E. J. BELASCO ◽  
S. K. GHOSH
Keyword(s):  
Regression Models ◽  
Continuous Variable ◽  
Continuous Variables ◽  
Multivariate Models ◽  
Mixture Regression ◽  
Potential Applications ◽  
Mixture Regression Models ◽  
Mixture Regression Model ◽  
The Relationship ◽  
Positive Half

SUMMARYThe present paper develops a mixture regression model that allows for distributional flexibility in modelling the likelihood of a semi-continuous outcome that takes on zero value with positive probability while continuous on the positive half of the real line. A multivariate extension is also developed that builds on past multivariate models by systematically capturing the relationship between continuous and semi-continuous variables, while allowing for the semi-continuous variable to be characterized by a mixture model. The flexibility associated with this model provides potential applications in many production system studies. The empirical model is shown to provide a more accurate measure of mortality rates in cattle feedlots, both independently and within a system including other performance and health factors.

scholarly journals Robust fitting of mixture regression models

2012 ◽  
Vol 56 (7) ◽  
pp. 2347-2359 ◽  
Author(s):  
Xiuqin Bai ◽  
Weixin Yao ◽  
John E. Boyer
Keyword(s):  
Regression Models ◽  
Mixture Regression ◽  
Robust Fitting ◽  
Mixture Regression Models

scholarly journals Poisson Mixture Regression Models for Heart Disease Prediction

2016 ◽  
Vol 2016 ◽  
pp. 1-10 ◽  
Author(s):  
Chipo Mufudza ◽  
Hamza Erol
Keyword(s):  
Heart Disease ◽  
Regression Model ◽  
Regression Models ◽  
Information Criteria ◽  
Disease Prediction ◽  
Poisson Mixture ◽  
Mixture Regression ◽  
Concomitant Variable ◽  
Mixture Regression Models ◽  
Mixture Regression Model

Early heart disease control can be achieved by high disease prediction and diagnosis efficiency. This paper focuses on the use of model based clustering techniques to predict and diagnose heart disease via Poisson mixture regression models. Analysis and application of Poisson mixture regression models is here addressed under two different classes: standard and concomitant variable mixture regression models. Results show that a two-component concomitant variable Poisson mixture regression model predicts heart disease better than both the standard Poisson mixture regression model and the ordinary general linear Poisson regression model due to its low Bayesian Information Criteria value. Furthermore, a Zero Inflated Poisson Mixture Regression model turned out to be the best model for heart prediction over all models as it both clusters individuals into high or low risk category and predicts rate to heart disease componentwise given clusters available. It is deduced that heart disease prediction can be effectively done by identifying the major risks componentwise using Poisson mixture regression model.

Sign in / Sign up

Export Citation Format

Share Document