https://blog.csdn.net/qq_29831163/article/details/89440215
Other blog posts in time series:
Time series model (1): model overview
Time series model (two): moving average method
Time series model (three): exponential smoothing method
Time series model (four): difference exponential smoothing method, adaptive filtering methodv
Time series model (5): Trend extrapolation forecasting method
Time series model (7): The basic steps of time series modeling
table of Contents
Different classifications of time series
Overview of deterministic time series analysis methods
Different classifications of time series
Time series are data series that are arranged in chronological order , change over time and are related to each other . The method of analyzing time series constitutes an important field of data analysis, namely time series analysis. Time series can have different classifications according to the research basis.
1. According to the number of points of the research object , there are one-dimensional time series and multiple time series.
2. According to the continuity of time, time series can be divided into discrete time series and continuous time series.
3. According to the statistical characteristics of the series , there are stationary time series and non-stationary time series. If the probability distribution of a time series has nothing to do with time t , the series is called a strict (narrow sense) stationary time series. If the first and second moments of the sequence exist , and for any time t satisfies:
(1) The mean value is constant
(2) Covariance is a function of time interval . The sequence is called a wide stationary time series, also called a generalized stationary time series. The time series we will study later are mainly wide stationary time series.
4. According to the distribution law of time series, there are Gaussian time series and non-Gaussian time series.
Overview of deterministic time series analysis methods
Time series forecasting technology is to study the trend of the forecast target's own time series. A time series is often the superposition or coupling of the following types of changes. We often think that a time series can be decomposed into the following four parts :
(1) Long-term trend changes . It refers to the tendency of a time series to continuously rise or fall in a certain direction, or stay at a certain level, and it reflects the main trend of changes in objective things.
(2) Seasonal changes .
(3) Cycle changes . Usually refers to fluctuations with a period of more than one year and similar fluctuations caused by non-seasonal factors.
(4) Irregular changes . Usually it is divided into sudden changes and random changes.
Three time series models
If within the forecast time range, there is no sudden change and the variance of the random change is small, and there is reason to believe that the evolution trend of the past and the present will continue to develop into the future, some empirical methods can be used to predict.
Other blog posts in time series:
Time series model (1): model overview
Time series model (two): moving average method
Time series model (three): exponential smoothing method
Time series model (four): difference exponential smoothing method, adaptive filtering methodv
Time series model (5): Trend extrapolation forecasting method
Time series model (7): The basic steps of time series modeling