1) Stationary Series

If following three conditions are satisfied then it is a stationary series

a) The mean of the function should be constant
b) The variance of the series should not be a function of time
c) The covariance of the i'th term and (i+m)'th term should not be a function
of time.
# Until unless our time series is stationary we cannot build a time series model
# A Random walk is not a stationary process (Variance & Covariance is time depen
dent)
# Stationary testing and converting a series into a stationary series are the mo
st critical processes in a time series modelling.
# AR or MA are not applicable on non-stationary series
# AR
x(t) = alpha * x(t-1) + error(t)
This equation is known as AR(1) formulation. The numeral (1) denotes that the ne
xt instance is solely dependent on the previous instance. The 'alpha' is a const
ant which reduces the error rate
# MA
x(t) = beta*error(t-1) + error(t)