Modelado matemático predictivo para la sostenibilidad de los emprendimientos productivos

Abstract

Executive Summary Models that explain and predict failure and success are very valuable to entrepreneurs in the production sector. The implementation of an explanatory and predictive mathematical - statistical model is presented for the study of the sustainability of productive enterprises in the Cevallos, Quero, Mocha, Patate and Tisaleo cantons of the province of Tungurahua, Ecuador. A logistic regression model is proposed and adjusted on a sample of 1546 entrepreneurs. The variable selection method is stepwise which, following the parsimonious principle, incorporates only the variables that are significant. The deviance goodness-of-fit test suggests that such a model fits the data appropriately. Several hypotheses are checked and discussed, the most important result being the demonstration that there are factors that can be used to explain the success of productive entrepreneurs. These are: Instruction, time of the undertaking, staff, canton and if it has been suspended.