SOME ASPECTS OF THE BAYESIAN APPROACH IN LINEAR REGRESSION ANALYSIS
Keywords:
Bayesian approach, regression model, a priori parameters, Monte Carlo method, multidimensional normal distribution.Abstract
It is shown that Bayesian methods are data analysis tools, which for small sample sizes allow us to evaluate regression models more fully and more accurately in comparison with classical statistical methods.
References
Hoff P. D. A First Course in Bayesian Statistical Methods / Peter D. Hoff. – Springer New York, 2009. – 276 p.
Зельнер А. Байесовские методы в эконометрии / А. Зельнер. – М.: Статистика, 1980. – 434 c.
Zellner A. On Assessing Prior Distributions and Bayesian Regression Analysis with g-Prior Distributions / A. Zellner // Bayesian Inference and Decision Techniques : Essays in Honor of Bruno de Finetti. – New York, North Holland Publishing Co., 1986. – Vol. 6. – P. 233–243.
Adler J. R in a Nutshell / J. Adler. – USA: O’Reilly Media, 2012. – 697 p.
Дрейпер Н., Смит Г. Прикладной регрессионный анализ / Н. Дрейпер , Г. Смит . – 3-е изд. – М.: Диалектика, 2007. – 912 с.
Ермаков С.М. Метод Монте-Карло в вычислительной математике. Вводный курс / С.М. Ермаков. – СПб: Бином. Лаборатория знаний, 2009. –192 c.
