This dissertation studies density estimation and portfolio selection problems using the maximum entropy (ME) principle. Since an entropy measure turns out to be a distance measure between two distributions, it can be used to estimate unknown density function. Entropy can be also interpreted as a measure of the degree of diversification and thus provides an useful way to construct optimal portfolio weights. In this dissertation three subjects are studied extensively. First, we propose ME autoregressive conditional heteroskedasticity model with demonstrating how we can extract informative functional from the data in the form of moment function. Second, the portfolio selection problem is considered using ME principle. We propose to use cross entropy measure as the objective function (to minimize) with side conditions coming from the mean and variance-covariance matrix of the resampled asset returns. Finally, using ME principle, we provided characterization of some well-known income distributions and flexible parametric income distributions which satisfy certain stylized facts of personal income data. Empirical results showed that maximum entropy principle is quite useful for analyzing economic and financial data.

This book is a collection of introductory, interdisciplinary articles and lectures covering the fundamentals of the maximum entropy approach, a powerful new technique that provides a much needed extension of the established principles of rational inference in the sciences. Maximum entropy allows the interpretation of incomplete and "noisy" data, providing a description of the underlying physical systems. It has found application in both practical and theoretical studies ranging from image enhancement to nuclear physics, and from statistical mechanics to economics. The work explores these applications with specific problems of data analysis taken from the physical sciences. It will interest all physical scientists who deal with data and its interpretation, including statisticians and statistical physicists.

This Is The First Comprehensive Book About Maximum Entropy Principle And Its Applications To A Diversity Of Fields Like Statistical Mechanics, Thermo-Dynamics, Business, Economics, Insurance, Finance, Contingency Tables, Characterisation Of Probability Distributions (Univariate As Well As Multivariate, Discrete As Well As Continuous), Statistical Inference, Non-Linear Spectral Analysis Of Time Series, Pattern Recognition, Marketing And Elections, Operations Research And Reliability Theory, Image Processing, Computerised Tomography, Biology And Medicine. There Are Over 600 Specially Constructed Exercises And Extensive Historical And Bibliographical Notes At The End Of Each Chapter.The Book Should Be Of Interest To All Applied Mathematicians, Physicists, Statisticians, Economists, Engineers Of All Types, Business Scientists, Life Scientists, Medical Scientists, Radiologists And Operations Researchers Who Are Interested In Applying The Powerful Methodology Based On Maximum Entropy Principle In Their Respective Fields.

This volume of Advances in Econometrics looks at applying maximum entropy to econometric problems and consists of two sections: the first section contains papers developing econometric methods based on the entropy principle; an interesting array of applications is presented in the second section of the volume.

In economics, many quantities are related to each other. Such economic relations are often much more complex than relations in science and engineering, where some quantities are independence and the relation between others can be well approximated by linear functions. As a result of this complexity, when we apply traditional statistical techniques - developed for science and engineering - to process economic data, the inadequate treatment of dependence leads to misleading models and erroneous predictions. Some economists even blamed such inadequate treatment of dependence for the 2008 financial crisis. To make economic models more adequate, we need more accurate techniques for describing dependence. Such techniques are currently being developed. This book contains description of state-of-the-art techniques for modeling dependence and economic applications of these techniques. Most of these research developments are centered around the notion of a copula - a general way of describing dependence in probability theory and statistics. To be even more adequate, many papers go beyond traditional copula techniques and take into account, e.g., the dynamical (changing) character of the dependence in economics.

The last two decades have witnessed an enormous growth with regard to ap plications of information theoretic framework in areas of physical, biological, engineering and even social sciences. In particular, growth has been spectac ular in the field of information technology,soft computing,nonlinear systems and molecular biology. Claude Shannon in 1948 laid the foundation of the field of information theory in the context of communication theory. It is in deed remarkable that his framework is as relevant today as was when he 1 proposed it. Shannon died on Feb 24, 2001. Arun Netravali observes "As if assuming that inexpensive, high-speed processing would come to pass, Shan non figured out the upper limits on communication rates. First in telephone channels, then in optical communications, and now in wireless, Shannon has had the utmost value in defining the engineering limits we face". Shannon introduced the concept of entropy. The notable feature of the entropy frame work is that it enables quantification of uncertainty present in a system. In many realistic situations one is confronted only with partial or incomplete information in the form of moment, or bounds on these values etc. ; and it is then required to construct a probabilistic model from this partial information. In such situations, the principle of maximum entropy provides a rational ba sis for constructing a probabilistic model. It is thus necessary and important to keep track of advances in the applications of maximum entropy principle to ever expanding areas of knowledge.

Forty years ago, in 1957, the Principle of Maximum Entropy was first intro duced by Jaynes into the field of statistical mechanics. Since that seminal publication, this principle has been adopted in many areas of science and technology beyond its initial application. It is now found in spectral analysis, image restoration and a number of branches ofmathematics and physics, and has become better known as the Maximum Entropy Method (MEM). Today MEM is a powerful means to deal with ill-posed problems, and much research work is devoted to it. My own research in the area ofMEM started in 1980, when I was a grad uate student in the Department of Electrical Engineering at the University of Sydney, Australia. This research work was the basis of my Ph.D. the sis, The Maximum Entropy Method and Its Application in Radio Astronomy, completed in 1985. As well as continuing my research in MEM after graduation, I taught a course of the same name at the Graduate School, Chinese Academy of Sciences, Beijingfrom 1987to 1990. Delivering the course was theimpetus for developing a structured approach to the understanding of MEM and writing hundreds of pages of lecture notes.