The estimation of the error in the definition of risk and return measures in modern portfolio theory (MPT): an analysis using mixture design experiment (MDE)

• Grant number: 17/09683-4
• Support Opportunities: Regular Research Grants
• Start date: November 01, 2018
• End date: October 31, 2019
• Field of knowledge: Engineering - Production Engineering - Economic Engineering
• Principal Investigator: Francisco Alexandre de Oliveira
• Grantee: Francisco Alexandre de Oliveira
• Host Institution: Faculdade de Engenharia (FEG). Universidade Estadual Paulista (UNESP). Campus de Guaratinguetá. Guaratinguetá , SP, Brazil

Abstract

The theory of resource allocation proposed by Markowitz (1952) has been widely investigated around the world. Initially proposed for resource allocation in financial assets. Currently, the model has evolved, with the variance of the optimization objective function for multi-objective optimization. Thus, it is possible to maximize returns while minimizing risk. This approach is widely used in many practical applications, ranging from commodity trading and investment decisions within a corporation. However, the model is generally treated in a deterministic way in which the solution is unique. The estimation errors of the parameters that define the behavior of financial returns can significantly affect portfolio performance found. The proposed research project is to study the behavior and portfolio optimization based on known as Design of Experiments in specific models Arrangement Mixing technique. This way, you can obtain an econometric model of the behavior of the variables of interest to a portfolio, ie, return and risk. Through this econometric model will be then possible to estimate the efficient frontier, which defines the best trade-off between risk and return, assuming a desired degree of confidence. Thus, the analyst can optimize the allocation of resources and perform statistical inferences on the results obtained, aiding decision making. (AU)