Identifiability of Longitudinal Regression Models with Response Variables Observed on (0, 1) or [0, 1]
Keywords:
Beta regression model, inflation, random effectAbstract
The identifiability problem is treated for mixtures involving two specific (0, 1) and {0, 1} supported distributions. It is proved and elaborated that two conditions are needed to achieve the model identifiability in a longitudinal beta regression model or a longitudinal zero and one inflated beta regression model: the model parameter vector does not contain any intercept, with all the domains
of the covariates containing at least one interval in the real numbers and zero. The techniques for establishing identifiability used here may be applied to other statistical models.
References
Cui X, Guo J, Yang G. On the identifiability and estimation of generalized linear models with parametric nonignorable missing data mechanism. Comput Stat Data Anal. 2017; 107: 64-80.
Culpepper SA. An exploratory diagnostic model for ordinal responses with binary attributes: Identifiability and estimation. Psychometrika. 2019; 84(4): 921-940.
Ferrari S, Cribari-Neto F. Beta regression for modelling rates and proportions. J Appl Stat. 2004; 31(7): 799-815.
Kieschnick R, McCullough BD. Regression analysis of variates observed on (0, 1): percentages, proportions and fractions. Stat Model. 2003; 3(3): 193-213.
Miao W, Ding P, Geng Z. Identifiability of normal and normal mixture models with nonignorable missing data. J Am Stat Assoc. 2017; 111(516): 1673-1683.
Ospina R, Ferrari SL. Inflated beta distributions. Stat Pap. 2010; 51(1): 111-126.
Ospina R, Ferrari SL. A general class of zero-or-one inflated beta regression models. Comput Stat Data Anal. 2012; 56(6): 1609-1623.
Verkuilen J, Smithson M. Mixed and mixture regression models for continuous bounded responses using the beta distribution. J Educ Behav Stat. 2012; 37(1): 82-113.
Wang, W. Identifiability of linear mixed effects models. Electron J Stat. 2013; 7: 244-263.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
