Bayesian Dynamic Model and Predictive Statistical Models
DOI:
https://doi.org/10.15665/rde.v15i1.547Keywords:
Bayesian model, Waste Analysis, Bayesian prediction, Automated EstimateAbstract
This paper, a practical application, proven through actual data, how the Bayesian Dynamic Linear Model Order 1 can be applied directly to the random waste from a multiple regression model Classic Static, thus creating an interesting addition is exposed for predictive statistical models. This Bayesian component generates a retro factor that feeds on waste (difference between predictions and actual historical values), adjusted according to the most recent historical information, all of them automatically and without the need to continually adjusts the Multiple Regression coefficients, generating an increase in the strength and stability of such models for prediction automated tools companies. This article provides a case of how Bayesian statistics can be an excellent complement to the techniques of classical frequentist statistics.
Resumen
Mediante este artículo, se expone una aplicación práctica, comprobada a través de datos reales, de cómo el Modelo Lineal Dinámico Bayesiano de Orden 1, puede ser aplicado directamente sobre los residuos aleatorios provenientes de un Modelo Clásico de Regresión Múltiple Estático, generando así un complemento interesante para los modelos estadísticos predictivos. Este componente bayesiano, genera un factor que se retro alimenta de los residuos (diferencia entre las predicciones y los valores históricos reales), ajustándose según la información histórica más reciente, todo ellos de forma automatizada y sin necesidad de ajustar continuamente los coeficientes de Regresión Múltiple, lo que genera un incremento en la robustez y estabilidad de dichos modelos para herramientas automatizadas de predicción en empresas. Este artículo establece un caso de cómo la estadística bayesiana puede ser un excelente complemento para las técnicas de las estadística clásica frecuentista.
Resumo
Através deste artigo, uma aplicação prática, comprovada através de dados reais, como o modelo linear dinâmico Bayesian Ordem 1 pode ser aplicado diretamente sobre os resíduos aleatória de um modelo clássico de regressão múltipla estático, gerando assim um suplemento exposta interessante para os modelos estatísticos preditivos. Este componente Bayesian gera um fator que retro alimenta de resíduos (diferença entre as previsões e os valores históricos reais), ajustado de acordo com as últimas informações históricas, todas elas automaticamente e sem a necessidade de ajustar continuamente os coeficientes de regressão múltipla , gerando um aumento na força e estabilidade de tais modelos para ferramentas de previsão automatizada empresas. Este artigo fornece um exemplo de como as estatísticas Bayesian pode ser um excelente complemento para as técnicas de estatística freqüentista clássicos.
References
Barrera, C. J. & Correa, J. C. (2008) Distribución predictiva bayesiana para modelos de pruebas de vida vía MCMC. Revista Colombiana de Estadística, (31)(2), 145–155.
Boada, A. J. & De Vasconcelos, D. (2013) Modelo estadístico de regresión múltiple, columna vertebral para predecir en empresas multinacionales con estilo de venta por catálogo. Revista Lasallista, (10)(1), 112 - 127.
Boada, A. & Mayorca, R. (2011) Planificación de Demanda, en Empresas con Estilo de Venta por Catálogo. Revista Lasallista, (8)(2), 124 - 135.
Bolstad, W. M. (2007) Introduction to Bayesian Statistics. Hamilton, NZ: Wiley.
Casado, R. & Montalvo F. (1998) Diseño de un Modelo Estadístico Predictivo, para las ventas, en unidades, de las diferentes líneas de labiales en barras de Avon Cosmetics de Venezuela C.A. (Trabajo de Grado). Caracas: Biblioteca de la Universidad Metropolitana (Físico). Escuela de Ciencias Administrativas.
Chambers, J. M. & Trevor J. Hastie (1992) Statistical Models in S. New York: Wadsworth & Brooks/Cole.
Chase, R.; Jacobs, R. & Aquilano, N. (2005) Administración de la Producción y Operaciones para una Ventaja Competitiva. Buenos Aires: McGraw Hill.
Diebold, F. X. (1998) Elements of Forecasting. San Diego: South Western College Publishing.
Malhotra, N. K. (1997) Marketing Research: An Applied Orientation. Georgia, ATL: Prentice Hall.
Klepacki, L. (2005) AVON La construcción de un imperio femenino. México: Editorial: Aguilar Kotler, P.
Armstrong, G. (1994) Mercadotecnia. México: Pearson.
Levin, Richard & David Rubin (1996). Estadística para Administradores. Buenos Aires: Prentice Hall.
Montgomery, D.; Peck, E. & Vinning, G. (2006) Introducción al Análisis de Regresión Lineal. México: Continental.
Pericchi, L. R. (2002) Análisis de Decisión, Inferencia y Predicción Estadística Bayesiana. Caracas: Universidad Simón Bolívar.
Schiffman, L. & Kanuk, L. (2010) Comportamiento del Consumidor. México: Pearson.
Tatsuoka, M. M. (1991) Multivariate Analysis: Techniques for Educational and Psychological Research. Chapaign: University of Illinois.
Valencia C., Marisol & Correa M., Juan C. (2013) Un Modelo Dinámico Bayesiano para el Pronóstico de Energía Diaria. Revista Ingeniería Industrial, (12)(2), 7-17.
Webster, A. L. (2000) Applied Statidtics for Business and Economics. New York: McGraw - Hill.
West, M. & Harrison, J. (1989) Bayesian Forecasting and Dynamic Models. New York: Springer - Verlag.
Downloads
Additional Files
Published
How to Cite
Issue
Section
License
Instructions for filling in the Certification of Originality and the Copyright Transfer:
Keep in mind that by pressing the "save and continue" button at the end, you are assuming all the ethical and legal commitments set forth herein. They establish the responsibilities of the legislation on intellectual property rights. For this it is assumed that whoever is carrying out the action of presenting the written work in good faith and represents himself and the other authors of the postulated article.
In this sense, the authors retain all the rights of which they are owners and authorize the free reproduction of the document sent. In the event of being necessary, they will assume, by pressing the "save and continue" button, the legal responsibility derived from the patrimonial rights which are free because of the non-payment by any procedure of the Journal.
Consequently, the author (s) represented by the person who advances the postulation of the article for evaluation and eventual publication,
I (We) declare:
1. I am (we are) the author (s) of the article {here is the name of the article placed automatically}.
2. This is an original work in accordance with the intellectual property law of Colombian copyright.
3. The content of the article of the reference has not been published and that it will not be submitted to any other means of publication in written or electronic support before knowing the decision of the Editorial Committee of Dimensión Empresarial.
4. The signer of this certification guarantees that the commitment acquired here does not infringe any third-party rights.
5. The publication authorization includes its electronic file and its adaptation, if necessary, for its incorporation in the network or in any electronic format or database, as well as attaching the necessary metadata to register the work, trademarks of water or any other security or protection system.
6. The publication authorization includes reproduction on digital media. As well as its distribution and making available through institutional archives through the Internet, distribute copies, and exhibit it in Colombia and outside the country, as well as include the article in national and international indexes.
7. The author assumes all responsibility, including compensation for damages, that could be exercised against the Universidad Autónoma del Caribe by third parties who violated their rights and interests because of the assignment.
For its part, Dimension Empresarial undertakes to respect in any case the rights of the author contained in Article 30 of Law 23 of 1982, or any after it and will make the article available to the users of the Journal so that make a legitimate use of it, as permitted by the applicable legislation, provided that its authorship is cited, commercial benefit is not obtained, and derivative works are not made.
The authors agree to accept the conditions of this intellectual property note, which will be applied to this submission when it is published in this journal.
