Answer ( 1 )

  1. swaplaw007
    0
    Reply

    d stands for the amount of differencing you need to apply to make the time series
    stationary.
    To get the value of d, you first conduct a Augmented Dicky Fuller Test to check for the
    stationarity of the time series. If the time series is not stationary, then you can take differences
    along the time series.
    Example, t- (t-1) , (t-1) – (t-2)……….
    Then, you conduct the ADF test to again to test for stationarity.
    You can continue this process until you get the stationarity, but generally it is not recommended
    that you take the differences more than 3 times.

    You can also use another method which is known as log differencing, where you first make the
    log transformation and then take the differences.

Leave an answer

Browse
Browse