Contents
How does cointegration of two time series work?
The two series are perfectly correlated and cointegrated since the difference between the two doesn’t change with time. Adding a slight phase shift to the above removes all correlation but still preserves cointegration. The below code snippet simulates three time series that share the same underlying random walk process.
Is the correlation coefficient and cointegration the same?
Although the correlation coefficient and cointegration both describe some underlying relationship between variables, the two properties are not synonymous. It is very possible for two time series to have weak/strong correlation but strong/weak cointegration. The two series are clearly correlated but the difference between them changes with time.
What was the original procedure for testing cointegration?
This is the original procedure for testing cointegration developed by Robery Engle and Clive Granger in their seminal paper Engle and Granger [1987]. The 2-step procedure is easy to follow and paints a good picture of the general idea behind cointegration.
Can You cointegrate two series with a phase shift?
The two series are clearly correlated but the difference between them changes with time. The two series are perfectly correlated and cointegrated since the difference between the two doesn’t change with time. Adding a slight phase shift to the above removes all correlation but still preserves cointegration.
When to use a cointegration test in data analysis?
A cointegration test is used to establish if there is a correlation between several time series Time Series Data Analysis Time series data analysis is the analysis of datasets that change over a period of time. Time series datasets record observations of the same variable over various points of time.
Which is the best example of cointegration theory?
Cointegration theory is de\fnitely the innovation in theoretical econometrics that has cre-ated the most interest among economists in the last decade. The de\fnition in the simple caseof 2 time series xt andyt, that are both integrated of order one (this is abbreviated I(1), andmeans that the process contains a unit root), is the following:
How is cointegration related to the correlation matrix?
The correlation matrix shows that those with larger cointegration coefficients (0.01, 0.05, and 0.1) show stronger correlation with the originating series. The time series with higher cointegration coefficients in their equation more closely follow the originating series.