Considering the time-series analysis, not as an abstract statistical concept and is widely used in practice, the phenomenon, we can conclude that this topic is very relevant today for the study of a number of processes.It is especially in demand in the economic activity of the person, so most of the examples in the scientific and popular literature are from the point of view of its use in this context.But the scope of the study and evaluation of the use of time series ends.
very definition of the time series in many ways reminds us of the process of gathering all the statistical information and is chёtkom fixing at certain intervals of real indicators measured way, giving the greatest reliability.In other words, in the description of any phenomenon used graph where the abscissa fixed measuring time indicators, and the ordinate of its actual physical size.
In fact, the methods of analysis of time series at one time formed the basis of the description of many physical laws and technical processes.Their synthesis has allowed the process to reduce the description to a specific mathematical expression.But not all the processes have been able to fit into the framework of clear formulas.A solution of two main problems has not been canceled.They are:
- determine the nature of the series;
- forecasting.
For analysis of time series received additional impetus to its development and in its arsenal appeared rich set of tools and methods.
classic example of the time series was a series proposed in 1976 by Box and Jenkins.For example, the study of the activity of international air traffic monthly for twelve years in the period 1949-1960 years, they have shown the existence of two components: the almost linear trend and seasonal changes.When the increase in traffic has steadily increased, and depending on the season periodically observed portions of the burst and damping activity.This type of description is called a model with multiplicative seasonality.
In the same year the same Box and Jenkins offered very interesting in terms of forecasting, but very time-consuming and difficult method of autoregressive integrated moving average (ARIMA).
the study of the processes subject to outside influence, the spread was a practical method of interrupted time series.It has been described in the 80s of the last century.The essence of the method lies in the study of the processes after the intervention of the system from the outside.Time series analysis was to assess the introduction of new management methods, the use of different know-how, influence lawmaking, etc.
Spectral analysis of time series appeared on the basis of previous methods.Among the evaluation criteria for this method is clearly visible during and frequency.Quite widely used in the calculation of complex numbers, Fourier transform.
abundance of methods and techniques that involves the analysis of time series confirms how fertile the ground for further research.For descriptions of these processes are cumbersome and require a certain experience from the analyst.A powerful leap in the development of personal computer technology has led to the conclusion of this type of analysis to a new level.But the ubiquity of the Internet has made available to the general category of the latest research in this area.
What is not time-series analysis, uses a successful player in the Forex market, it is the study of the graphs of the company allows a manager to develop a true strategic line, and assessment of the market provides a vast field for marketers and managers, allowing you to adjust the level of prices and range of products sold orservices in order to obtain maximum benefit.
Each method of analysis deserves special attention and requires thorough investigation.And if you have any of them interested, the purpose of the article is achieved.
