Multivariate measurement error models based on Student-t distribution under censored responses

Author(s)

Matos, Larissa A. ^[1] ; Castro, Luis M. ^[2] ; Cabral, Celso R. B. ^[3] ; Lachos, Victor H. ^[4]

Affiliation

^[1] Univ Estadual Campinas, IMECC, Dept Stat, BR-13083859 Campinas, SP - Brazil

^[2] Pontificia Univ Catolica Chile, Dept Stat, Santiago - Chile

^[3] Univ Fed Amazonas, Dept Stat, Manaus, Amazonas - Brazil

^[4] Univ Connecticut, Dept Stat, Storrs, CT 06269 - USA

• Document type: Journal article
• Source: STATISTICS; v. 52, n. 6, p. 1395-1416, 2018.
• Web of Science Citations: 0

Abstract

Measurement error models constitute a wide class of models that include linear and nonlinear regression models. They are very useful to model many real-life phenomena, particularly in the medical and biological areas. The great advantage of these models is that, in some sense, they can be represented as mixed effects models, allowing us to implement wellknown techniques, like the EM-algorithm for the parameter estimation. In this paper, we consider a class of multivariate measurement error models where the observed response and/or covariate are not fully observed, i.e., the observations are subject to certain threshold values below or above which the measurements are not quantifiable. Consequently, these observations are considered censored. We assume a Student-t distribution for the unobserved true values of the mismeasured covariate and the error term of the model, providing a robust alternative for parameter estimation. Our approach relies on a likelihood-based inference using an EM-type algorithm. The proposed method is illustrated through some simulation studies and the analysis of an AIDS clinical trial dataset. (AU)

• FAPESP's process: 15/20922-5 - Flexible regression modeling for censored data
• Grantee: Víctor Hugo Lachos Dávila
• Support Opportunities: Research Grants - Visiting Researcher Grant - Brazil
• FAPESP's process: 18/05013-7 - Semiparametric mixed effects models with multiple censored response using scale mixtures of normal distributions
• Grantee: Larissa Avila Matos
• Support Opportunities: Research Grants - Visiting Researcher Grant - International
• FAPESP's process: 15/05385-3 - Estimation in mixed-effects models with censored response using scale mixtures of normal distributions
• Grantee: Larissa Avila Matos
• Support Opportunities: Scholarships abroad - Research Internship - Doctorate
• FAPESP's process: 11/22063-9 - APPLICATIONS OF THE SCALE MIXTURES OF SKEW-NORMAL DISTRIBUTIONS IN FACTOR ANALYSIS MODELS
• Grantee: Larissa Avila Matos
• Support Opportunities: Scholarships in Brazil - Doctorate