Bayesian Data Analysis in Modeling and Forecasting Nonlinear Nonstationary Financial and Economic Processes

EasyChair Preprint 9376, version 1

Abstract

A short review of modern Bayesian methods for data analysis is presented that shows wide applicability of the methods mentioned in many areas of practical human activities. Some application details are provided for generalized linear models, that are popular in analysis of NNP, to highlight their possibilities and specific features. All Bayesian techniques of data analysis are very popular today thanks to their flexibility, high quality of final results, availability of possibilities for adaptation to new data and conditions of functioning. Besides, each of these approaches to data analysis is well supported by appropriate sets of statistical criteria that make possible thorough quality analysis of intermediate and final results. Illustrative example is presented of GLM application providing an insight into some possibilities and special features of the methods. Some considerations are provided regarding development and practical application of specialized intellectual decision support system directed to refinement and quality enhancement of computational results and providing intellectual help to users.

Keyphrases: Bayesian methods, Forecasting, generalized linear models, modeling, nonlinear nonstationary processes

@booklet{EasyChair:9376,
  author    = {Oleksandr Trofymchuk and Petro Bidyuk and Tatyana Prosiankina-Zharova and Oleksandr Terentiev},
  title     = {Bayesian Data Analysis in Modeling and Forecasting Nonlinear Nonstationary Financial and Economic Processes},
  howpublished = {EasyChair Preprint 9376},
  year      = {EasyChair, 2022}}