Supplementary material – Time series
Concept of STATIONARITY
A stochastic process is said to be weakly, covariance or second-order stationary if its:
The mean is constant:
The variance is constant:
the value of covariance between two periods depends only on the distance or gap between the two time periods and not the actual time at which the covariance is computed. Example
The autocovariance depends on the lag difference and not when the variable is observed:
e.g. (i) One lag difference:
(ii) Two lag difference:
Where , the covariance (or autocovariance) at lag k, is the covariance between the values of and that is, between two X values k periods apart.
If k=0, we obtain which is simply the variance of X (=).
2. AUTOREGRESSIVE TIME SERIES (AR)
The simplest, purely statistical time series model is the first order autoregression, or AR(1) process;
where
In this case n lags of X are deemed to be important in determining the time series behaviour of X.
The stationarity is imposed by .
Note: Once any of the covariance stationarity characteristics is violated, then we have non-stationarity!!!!
Share with your friends: |