Document Type : Authored Book

Authors

• Javad Ghasemian
• Rahman Farnoosh

School of Mathematics and Computer Science, Damghan University, Damghan, Iran

Abstract

This book offers a sophisticated journey beyond classical regression, exploring advanced methodologies essential for modeling complex, real-world data where traditional assumptions often break down. It begins by contrasting static regression models with dynamic time series models, establishing a foundational understanding of data analysis frameworks.
The core of the book is dedicated to powerful alternatives to classical regression, including:

Non-Parametric and Semi-Parametric Regression: Flexible methods that do not assume a fixed model form.
Fuzzy Regression: A pioneering approach designed to handle ambiguity, imprecision, and uncertainty in data. This method replaces crisp inputs with fuzzy numbers, making it ideal for situations where relationships between variables are not absolute.

The text positions fuzzy logic as a philosophical and practical extension of classical Aristotelian logic, arguing that many real-world phenomena are not "black and white" but exist in a "gray" area. Fuzzy regression provides the mathematical framework to model these nuances.
Structured to guide readers from parametric (linear and non-linear) to non-parametric and finally to fuzzy regression, this book is an invaluable resource for graduate students (Masters and PhD levels) and researchers in statistics, data science, and related fields. It synthesizes the authors' extensive experience in supervising advanced research, making it a practical guide for tackling modern analytical challenges in the era of big data.
 

Cover

Main Subjects

• Mathematics

ISBN: 9786225209091