Regression models: Extensions and applications

Acronym

P_REG-EXT

Consortium Coordinator

Sal Y Rosas Celi, Victor Giancarlo

Start Date

March 1, 2017

End Date

February 28, 2019

Status

https://purl.org/pe-repo/concytec/estadoProyecto#concluido

Tipo de proyecto

https://purl.org/pe-repo/ocde/tipoProyecto#investigacionBasica

Description

Regression models are statistical tools to explain one variable as a function of others. There are applied in several areas of sciences such as education, medicine, and engineering, among others. In education, one may be interested in a) studying whether or not a student¿s drop out from school base on his/her performance during semesters, family income, and other factors (Pebes, 2015 and Rojas 2016). In the area of medicine, one is interested in a) measuring the time to the development a disease and how that is affected by an intervention and other covariates (Sal y Rosas, 2011, 2010), b) estimating the proportion of cases of a disease (prevalence). In this grant, we proposed to extend several regression models in key areas: a) survival analysis by using copula model and outcome misclassification to model time to event interval censored data, b) estimation of prevalence with test subject to misclassification using Bayesian inference, c) to develop a Bayesian approach to model the graduation process at our university, d) to develop a Bayesian approach for model where the outcome variable is limited and has panel structure. The data that generates these hard problems come from our collaboration with a) the University of Washington, b) el Centro de Excelencia en Enfermedades Crónicas, and c) the Pontificia Universidad Católica del Perú.

Keywords

Modelos de regresión

;

Extensiones estadísticas

;

Aplicaciones

;

Inferencia

Área de conocimiento

Natural sciences

Campo OCDE

https://purl.org/pe-repo/ocde/ford#1.01.03