Modelo ARIMA para el pronóstico de la producción de cacao en el Perú 2012-2018

• Autor: Sánchez Sánchez, David Alexander
• Formato: tesis de grado
• Fecha de Publicación: 2018
• Institución: Universidad Nacional de Trujillo
• Repositorio: UNITRU-Tesis
• Lenguaje: español
• OAI Identifier: oai:dspace.unitru.edu.pe:20.500.14414/11563
• Enlace del recurso: https://hdl.handle.net/20.500.14414/11563
• Nivel de acceso: acceso abierto
• Materia: Metodología Box-Jenkins; Producción de cacao; SARIMA

This study is of descriptive observational longitudinal type, with tendency, having like main_x000D_ objective to determine a model of forecast that better explains the behavior of the monthly_x000D_ production of cacao, using information of the Central Bank of Reserve of Peru (BRCP) from the period January 2012 - July 2018, this being an applied investigation. The applied_x000D_ statistical methodology was the one proposed by Box-Jenkins and the series was divided_x000D_ into: january 2012 to july 2017 for the estimation of the model and from august 2017 to july 2018 for the validation of the forecast, this statistical technique is in charge of describing the characteristics of the series, in terms of its components of interest such as its trend and stationarity as well as predicting future values of the variable, the processing of them was carried out with the statistical program Eviews 9.5 and the Microsoft Excel 2016 program to compare the results. Finally, it was concluded that the model identified was a series of stationary trend and the predicted model was SARIMA (7,1,7) (1,1,0)12, whose equation is es Δ ̂ = −0.87−7 + 0.57−7 − 0.43−8−0.89−12 + the suitability of the model being tested. The monthly production was forecast from august 2018 to december 2018 and the forecasts were evaluated with: A Mean Absolute Deviation (AMD) of 80 tons of cocoa, a Mean Square Error (EMC) of 531 tons of poop, an average Error Percentage Absolute (PEMA) of 5.6% and the Mean Percentage of Error (PME) of 4% with respect to the original values