Un modelo vectorial de corrección de errores para la estimación del ingreso nacional del Perú

• Autor: Huaylla Salazar, Edinson
• Formato: tesis de grado
• Fecha de Publicación: 2023
• Institución: Universidad Nacional de Trujillo
• Repositorio: UNITRU-Tesis
• Lenguaje: español
• OAI Identifier: oai:dspace.unitru.edu.pe:20.500.14414/18319
• Enlace del recurso: https://hdl.handle.net/20.500.14414/18319
• Nivel de acceso: acceso abierto
• Materia: Modelos multivariantes no estacionarios VAR y VEC; Contrastes de cointegración

Traditionally, univariate models in time series are studied, such as the ARIMA model, and _x000D_ from this model there is an extension to multivariate VAR models and VEC models that are _x000D_ stationary and non-stationary. For non-stationary multivariate models, it is required to prove _x000D_ that the null hypothesis is non-stationary by means of the cointegration tests, with the objective _x000D_ of determining that the cointegration tests based on the VAR and VEC models are applicable in _x000D_ non-stationary multivariate models. The research that presents a study of applied, explanatory _x000D_ approach, studying the VAR and VEC models through the methodologies of the Dicker-Fuller _x000D_ Augmented Test and the method of the first differences, as well as the information criteria, _x000D_ including an example to be able to prove that the series of the models comply with the theory, obtaining that the series of the models are applicable in non-stationary multivariate models. It was concluded that the two models are applicable to long-term time series, and that both models have a common trend