Bibliographic citations
Castillo, R., (2022). Evaluación de los factores asociados a la producción de petróleo en el Perú mediante el análisis multivariante durante el periodo 2016-2020 [Tesis, Universidad Nacional de Ingeniería]. https://repositorio.uni.edu.pe/handle/20.500.14076/22728
Castillo, R., Evaluación de los factores asociados a la producción de petróleo en el Perú mediante el análisis multivariante durante el periodo 2016-2020 [Tesis]. PE: Universidad Nacional de Ingeniería; 2022. https://repositorio.uni.edu.pe/handle/20.500.14076/22728
@misc{renati/712094,
title = "Evaluación de los factores asociados a la producción de petróleo en el Perú mediante el análisis multivariante durante el periodo 2016-2020",
author = "Castillo Ramos, Rodrigo Alonso",
publisher = "Universidad Nacional de Ingeniería",
year = "2022"
}
Oil is an essential energy resource for the industrial development of Peru and the production of this hydrocarbon has been very changeable during the last years, therefore it is necessary to identify and analyze the dynamics of the Peruvian market. For this, an identification analysis of the Political, Economic, Social, Technological, Ecological and Legal variables (PESTEL) was carried out; to determine the variables involved in the external macro environment of the activity under study, then continued with the construction of two statistical models, i) factor analysis with multiple linear regression analysis and ii) the direct application of multiple linear regression analysis, both using the backward method. The statistical construction was carried out using IBM SPSS Statistics software for the period from 2016 to 2020, in order to find the best representation based on the variables of the macroeconomic external environment. After that, two constructed models were compared, to choose the optimal model that best represents the dependent variable and the existing criteria of the models were checked for validity. The results indicated that the coefficient statistics 𝑅2 were 0.509 and 0.820 respectively. The findings indicated that the optimal model was the second statistical model, but with the inclusion of ten variables from the initial total. Quite different from the first model which managed to use almost all variables but with a lower value of the statistic, this may explain the relationship of guidelines or parameters applicable in the design or redesign of measures that help to minimize the impact of the variation in oil production in future crises or other situations of a global context.
This item is licensed under a Creative Commons License