Foundations and Trends® in Econometrics > Vol 2 > Issue 1–2

Information and Entropy Econometrics — A Review and Synthesis

By Amos Golan, Department of Economics, American University, USA, agolan@american.edu

 
Suggested Citation
Amos Golan (2008), "Information and Entropy Econometrics — A Review and Synthesis", Foundations and Trends® in Econometrics: Vol. 2: No. 1–2, pp 1-145. http://dx.doi.org/10.1561/0800000004

Publication Date: 26 Feb 2008
© 2008 A. Golan
 
Subjects
Estimation frameworks
 

Free Preview:

Download extract

Share

Download article
In this article:
1. Introductory Statement, Motivation, and Objective 
2. Historical Perspective 
3. Information and Entropy — Background, Definitions, and Examples 
4. The Classical Maximum Entropy Principle 
5. Information-Theoretic Methods of Estimation — I: Basics and Zero Moments 
6. Information-Theoretic Methods of Estimation — II: Stochastic Moments 
7. IT, Likelihood and Inference — Synthesis via a Discrete Choice, Matrix Balancing Example 
8. Concluding Remarks and Related Work Not Surveyed 
References 

Abstract

The overall objectives of this review and synthesis are to study the basics of information-theoretic methods in econometrics, to examine the connecting theme among these methods, and to provide a more detailed summary and synthesis of the sub-class of methods that treat the observed sample moments as stochastic. Within the above objectives, this review focuses on studying the inter-connection between information theory, estimation, and inference. To achieve these objectives, it provides a detailed survey of information-theoretic concepts and quantities used within econometrics. It also illustrates the use of these concepts and quantities within the subfield of information and entropy econometrics while paying special attention to the interpretation of these quantities. The relationships between information-theoretic estimators and traditional estimators are discussed throughout the survey. This synthesis shows that in many cases information-theoretic concepts can be incorporated within the traditional likelihood approach and provide additional insights into the data processing and the resulting inference.

DOI:10.1561/0800000004
ISBN: 978-1-60198-104-2
152 pp. $99.00
Buy book (pb)
 
ISBN: 978-1-60198-105-9
152 pp. $125.00
Buy E-book (.pdf)
Table of contents:
1. Introductory Statement, Motivation and Objective
2. Historical Perspective
3. Information and Entropy - Background, Definitions and Examples
4. The Classical Maximum Entropy Principle
5. Information Theoretic Methods of Estimation - I: Basics and Zero Moments
6. Information Theoretic Methods of Estimation - II: Stochastic Moments
7. IT, Likelihood and Inference - Synthesis via a Discrete Choice, Matrix Balancing Example
8. Concluding Remarks and Related Work Not Surveyed
References

Information and Entropy Econometrics

Information and Entropy Econometrics - A Review and Synthesis summarizes the basics of information theoretic methods in econometrics and the connecting theme among these methods. The sub-class of methods that treat the observed sample moments as stochastic is discussed in greater details.

Information and Entropy Econometrics - A Review and Synthesis focuses on inter-connection between information theory, estimation and inference, provides a detailed survey of information theoretic concepts and quantities used within econometrics and then show how these quantities are used within IEE, and pays special attention for the interpretation of these quantities and for describing the relationships between information theoretic estimators and traditional estimators. Readers need a basic knowledge of econometrics, but do not need prior knowledge of information theory. The survey is self contained and interested readers can replicate all results and examples provided. Whenever necessary the readers are referred to the relevant literature.

Information and Entropy Econometrics - A Review and Synthesis will benefit researchers looking for a concise introduction to the basics of IEE and to acquire the basic tools necessary for using and understanding these methods. Applied researchers can use the book to learn improved new methods, and applications for extracting information from noisy and limited data and for learning from these data.

 
ECO-004