Multivariate Conditional Transformation Models. Application to Thyroid-Related Hormones

Autor:	Carla Díaz-Louzao, Carmen Cadarso-Suárez, Óscar Lado-Baleato, Francisco Gude
Rok vydání:	2021
Předmět:	Correlation Multivariate statistics Thyroid-stimulating hormone Statistics Covariate Generalized additive model Marginal distribution Mathematics Copula (probability theory) Hormone
Zdroj:	Computational Science and Its Applications – ICCSA 2021 ISBN: 9783030866525 ICCSA (1)
Popis:	Multivariate Conditional Transformation Models (MCTMs) were recently proposed as a new multivariate regression technique. These models characterize jointly the covariates effects on the marginal distributions of the responses and their correlations without requiring parametric assumptions. Flexibility, in both the responses and covariates effects are achieved using Bernstein basis polynomials. In this paper we compare MCTMs estimations with the well established Copula Generalized Additive Models (CGAMLSS). MCTMs conditional correlation estimations outperform the CGAMLSS ones, showing lower estimation error, and variability. Finally, MCTMs were applied to the joint modelling of three thyroid hormones concentrations – Thyroid Stimulating Hormone (TSH), triiodothyronine (T3), and thyroxine (T4) – conditionally on age. Our results show how the marginal distribution and correlations of the hormones concentrations are influenced by the age of the patients.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::4e491a87fc3f329d2e0e5ee6e09d50fe https://doi.org/10.1007/978-3-030-86653-2_25 Zobrazit plný text záznamu