Monitoring of a condition of economic systems on the basis of the analysis of dynamics of entropy A.N. Tyrsin 1, O.V. Vorfolomeeva 2 1 – Science and Engineering.

Slides:



Advertisements
Similar presentations
Methods for investigating zoning effects Mark Tranmer CCSR.
Advertisements

Design of Experiments Lecture I
Taking Stock Of Measurement. Basics Of Measurement Measurement: Assignment of number to objects or events according to specific rules. Conceptual variables:
Simple Regression. Major Questions Given an economic model involving a relationship between two economic variables, how do we go about specifying the.
STAT 497 APPLIED TIME SERIES ANALYSIS
Markov processes in a problem of the Caspian sea level forecasting Mikhail V. Bolgov Water Problem Institute of Russian Academy of Sciences.
Functions of Statistics
Review of Basic Probability and Statistics
Statistics for Business and Economics
Lec 6, Ch.5, pp90-105: Statistics (Objectives) Understand basic principles of statistics through reading these pages, especially… Know well about the normal.
Chapter 2 – Tools of Positive Analysis
Chapter 11 Multiple Regression.
November 14, 2014 Objectives: ◦ Differentiate between independent variables, dependent variables, and constants ◦ Explain how to carry out a scientific.
Economic Indexes Indexes in statistics Indexes are indicators of size comparison of any socio-economic process. Index number measures how much a variable.
Chapter 2: The Research Enterprise in Psychology
Chapter 2: The Research Enterprise in Psychology
A U.S. Department of Energy Office of Science Laboratory Operated by The University of Chicago Argonne National Laboratory Office of Science U.S. Department.
QNT 531 Advanced Problems in Statistics and Research Methods
Probabilistic and Statistical Techniques 1 Lecture 24 Eng. Ismail Zakaria El Daour 2010.
Topics: Statistics & Experimental Design The Human Visual System Color Science Light Sources: Radiometry/Photometry Geometric Optics Tone-transfer Function.
On project probabilistic cost analysis from LHC tender data Ph. Lebrun CERN, Geneva, Switzerland TILC’09, Tsukuba, Japan April 2009.
Understanding Numerical Data
LECTURE 2. GENERALIZED LINEAR ECONOMETRIC MODEL AND METHODS OF ITS CONSTRUCTION.
© 2001 Prentice-Hall, Inc. Statistics for Business and Economics Simple Linear Regression Chapter 10.
The Research Enterprise in Psychology
Decision Making Under Uncertainty and Risk 1 By Isuru Manawadu B.Sc in Accounting Sp. (USJP), ACA, AFM
Geo597 Geostatistics Ch9 Random Function Models.
Various topics Petter Mostad Overview Epidemiology Study types / data types Econometrics Time series data More about sampling –Estimation.
Copyright  2003 by Dr. Gallimore, Wright State University Department of Biomedical, Industrial Engineering & Human Factors Engineering Human Factors Research.
6 - 1 © 1998 Prentice-Hall, Inc. Chapter 6 Sampling Distributions.
Copyright © Allyn & Bacon 2007 Chapter 2 Research Methods This multimedia product and its contents are protected under copyright law. The following are.
FAT TAILS REFERENCES CONCLUSIONS SHANNON ENTROPY AND ADJUSTMENT OF PARAMETERS AN ADAPTIVE STOCHASTIC MODEL FOR RETURNS An adaptive stochastic model is.
Random Variables (1) A random variable (also known as a stochastic variable), x, is a quantity such as strength, size, or weight, that depends upon a.
Question paper 1997.
Science Process Skills Vocabulary 8/17/15. Predicting Forming an idea of an expected result. Based on inferences.
Chapter 10 Correlation and Regression Lecture 1 Sections: 10.1 – 10.2.
EMPLOYMENT AND EARNINGS James and Clayton. Topic of Interest Describes the economic status of all businesses in Canada (trends) Helps with determining.
© 2006 by The McGraw-Hill Companies, Inc. All rights reserved. 1 Chapter 12 Testing for Relationships Tests of linear relationships –Correlation 2 continuous.
1-4: Economist’s Toolbox  Everybody engages in economics (decisions)  Economists study these decisions and look to explain or even predict econ. Outcomes.
Information Geometry and Model Reduction Sorin Mitran 1 1 Department of Mathematics, University of North Carolina, Chapel Hill, NC, USA Reconstruction.
STATISTICS AND OPTIMIZATION Dr. Asawer A. Alwasiti.
1 Probability and Statistical Inference (9th Edition) Chapter 4 Bivariate Distributions November 4, 2015.
Sampling Theory and Some Important Sampling Distributions.
1-2: Scientific Inquiry What role do models, theories, and laws play in scientific investigation?
STA347 - week 91 Random Vectors and Matrices A random vector is a vector whose elements are random variables. The collective behavior of a p x 1 random.
6 - 1 © 2000 Prentice-Hall, Inc. Statistics for Business and Economics Sampling Distributions Chapter 6.
STATISTICS People sometimes use statistics to describe the results of an experiment or an investigation. This process is referred to as data analysis or.
Introduction Dispersion 1 Central Tendency alone does not explain the observations fully as it does reveal the degree of spread or variability of individual.
CORRELATION-REGULATION ANALYSIS Томский политехнический университет.
Psychology 101: General  Chapter 1Part 2 Scientific Method Instructor: Mark Vachon.
Chapter 9 Introduction to the t Statistic
Quantitative Methods in the Behavioral Sciences PSY 302
Determining How Costs Behave
Chapter 2: The Research Enterprise in Psychology
ESTIMATION.
Bell Work
Economics Unit 1: Individual, Business, & Government Choices
Behavioral Statistics
12 Inferential Analysis.
Labour Migration in Ukraine: trends and consequences
Understanding Psychology Unit 1 Chapters 1 & 2.
12 Inferential Analysis.
Research in Psychology
Lecture # 2 MATHEMATICAL STATISTICS
Continuous Random Variables 2
Chapter 10 Introduction to the Analysis of Variance
Lecturer Dr. Veronika Alhanaqtah
Copyright © Allyn & Bacon 2007
INTRODUCTION TO STATISTICS
Presentation transcript:

Monitoring of a condition of economic systems on the basis of the analysis of dynamics of entropy A.N. Tyrsin 1, O.V. Vorfolomeeva 2 1 – Science and Engineering Center «Reliability and Resource of Large Systems and Machines», Ural Branch, Russian Academy of Sciences, Ekaterinburg 2 – Chelyabinsk Stat University, Chelyabinsk

2 Entropy role in difficult, open systems Prigogine I.: Bifurcation – turning point in system development: choice from several new conditions; bifurcations are provoked by change of the operating parameter of system, entropy increase. Overcoming of a point of bifurcation is accompanied by decrease in entropy, self-organization. Klimontovich U.L.: There is "a norm of a randomness" (entropy level) for normal functioning of system; deviations from norm mean "illness". If "treatment" approaches a condition of open system to norm, self-organization process takes place Entropy characterizes system functioning.

3 S -multidimensional random variable If the random vector Y has a multidimensional normal distribution then

4 Entropy - probabilistic model Y1Y1 Y2Y2 Y3Y3 Y4Y4 Y5Y5 growth points H(Y 2 ) H(Y 3 )H(Y 1 ) H(Y 5 )H(Y 4 ) The Entropy - probabilistic model allows to allocate elements of difficult system and communication between them as separate variables System and its components :

5 Statement 1. Let X 1, X 2 - two continuous random variables with the finite variances, defined on the all numerical axis and described by one-type distributions. Then  1 2,  2 2, 1, 2 – variances and parameters of scale of random variables X 1 и X 2.

6 Example 1. 1) For normally distributed random variables X 1 and X 2 with variances  1 2 and  2 2 the difference of entropies is equal 2) For exponential distributed random variables X 1 and X 2 with scale parameters 1, 2 the difference of entropies is equal 3) Let's consider random variables X 1 and X 2, distributed under the lognormalny law with parameters of scale, and form parameter s. Entropy for the lognormalny law with scale parameters and form s is equal Taking into account that dispersion is equal, receive

7 Statement 2. Let we have two systems of continuous random variables and Then the difference of joint entropies of system of random variables is equal

8 where  the coefficients of determination of the corresponding dependences

9 Denoting we will present the system as where,  it is the increments of entropy at the expense of changes of dispersions and correlations of random variables.

10 The analysis of entropy-dynamic model in economics There are following ideas in economics that are underlay in the practical application of entropy-dynamic model: Hypothesis : The behavior of system can be considered as stochastic Formation of system of signs by means of the factorial analysis Monitoring of a condition of system in dynamics (analysis of change of entropy)

11 Example 2. Let's consider the list of macroeconomic indicators from the section "Main Socio-economic Indexes of the Russian Federation" annually published by the State committee on statistics of the Russian Federation of collections "Russia in Figures" from 2000 to It was established on the basis of the factorial analysis that the initial system can be represented in the form of three factors (main components) which are explained by 93,2% of all variation of initial signs. Factor: Y 1 – national wealth, factor Y 2 – deficiency (surplus) of the budget taking into account a rate of national currency and unemployment rate in the country, factor Y 3 – price index of producers of the industry.

12 Then, let's carry out the comparative analysis of behavior of a macro system in two periods (before 2005 and after) on the basis of the analysis if entropy of a random vector. Then we will receive This result can testify to deterioration of macroeconomic indicators in the second period integrally, caused by the economic crisis in comparison with the fact that the first period was characterized by the growth of economic development of the country.

13 The analysis of change of each of a component shows that the growth of entropy of a randomness was affected mostly by the second element of the system (Y 2 ) and on the increase in entropy of self-organization - weakening of the interaction between components Y 1 and Y 2.

14 Entropy modeling of dynamics of stochastic system is offered. In it's basis there is a representation of the system in the form of the random vector. Each of vector's components presents a continuous random variable. This approach allows solving problems of monitoring of the condition of stochastic systems in economics. Entropy - dynamic model doesn't show quantitative change of studied parameters, but gives deeper assessment of influence of this change. For example, if it is known that any average value of a quantitative index went down, then with the help entropy – dynamic the dynamic model could answer whether this decrease was uniform and organized or not. Entropy-dynamic model investigates the system fully. Results can be received both on separate elements of the system, and on the whole system that is almost impossible to analyze at a quantitative assessment of indicators of system. Conclusions :