Content
- Introduction
- Recovery model
- Monster series model
- Extension of the classical linear model
- General structure of the line
- Recovery model
- Mixed model
- Sometimes healing
- Self-construction
- Quantile regression
- Matrix Algebra
- Probability calculation and statistical presentation
- Normal distribution
- Conclusion
- Bayesian inference
- Bibliography
- Phonebook
Preface
Regression is a common and widely used statistical method for analyzing empirical problems in the social, economic and life sciences. Similarly, there are many different types of models and empirical tools, from standard linear regression to modern semi-nonparametric models. Currently available literature focuses mainly on specific regression models, but these vary greatly in methodology, statistical level, and theoretical orientation or application. So why another book on regression? Many introductory books are available for students and practitioners in various applications, but they only cover the background. Most texts, on the other hand, focus on modern methods that are not the same as semiparametric methods, essentially telling the reader that they have theoretical and practical advantages based on high-level statistics. Therefore, they cannot reach the adult readers who need to use this method.
The aim of this book is to apply and integrate regression, non-parametric and semi-parametric regression methods to bridge the gap between theory and practice. Basic sampling and regression methods are presented in a practical way and the methodology is explained using practical examples and case studies. The availability of (user-friendly) software was a criterion for the method chosen and presented. In our opinion, the connection and balance between theory and practice are essential for progress in applied science, as well as for the development of statistical methods, stimulated and stimulated by new challenges arising from various collaborations. A similar approach, but with different purposes, was followed in the book Semiparametric Regression by Ruppert, Wand, and Carroll (2003). Therefore, our book is aimed primarily at an audience of students, teachers, and practitioners in the social, economic, and health sciences, as well as students and teachers in statistical programs, and mathematicians and computer scientists interested in statistical modeling and data analysis. It is written at an intermediate level of mathematics and assumes only basic knowledge of probability, mathematics, and statistics. Brief sections of text that provide details or additional information begin with an apostrophe and end with a comma. These sections can be removed from the first reading without loss of continuity. Main features and details are summarized on the box. Two appendices describe the necessary matrix algebra as well as elements of probability and arithmetic calculations.
Depending on the area of interest, some parts of the book can be read independently of others or in the following order:
• Chapter 2 provides an introductory overview of logistic, nonparametric, and semiparametric regression methods, deliberately omitting technical information and empirical material.
• Chapters 1-4 can be read as an introduction to the model.
• Mixed Verses (chapters 7.1-7.4) can be studied immediately after chapter 4. 1-4 and before chapter. 5 and 6.
• Sections 10.1 and 10.2 on parallel lines can be read immediately after Section 1. 1-4.
• Chapters 1-4, chapters. 7. 1-7. 4 and chapter. 8-10 can be read as an introduction to semiparametric regression for continuous variables (including semiparametric quantile regression).
• Chapters 1-6 consist of regression models for continuous and discrete variables.
An overview of the possible measured values is given in the table below (parts between brackets
Download For Free in PDF Format