Time Series Analysis Package
STATIONARITY Object
The STATIONARITY class object functions perform the stationarity tests on a time series and store all the results that you can retrieve later by using the OUTSTATIONARITY object.
Table 24 summarizes the methods that are associated with the STATIONARITY object.
Table 24: Methods of the STATIONARITY Object
Figure 15 diagrams the methods of the STATIONARITY object.
Figure 15: STATIONARITY Data Flow
STATIONARITY Synopsis
DECLARE OBJECT obj (STATIONARITY);
Method syntax, in order of typical usage:
rc=obj.SetY (YSeries);
rc=obj.SetOption ('Name',Value <,'Name',Value, …> );
rc=obj.SetLags (Value);
rc=obj.SetDiff (Value);
rc=obj.Run ();
STATIONARITY Methods
STATIONARITY.Initialize Method
rc=obj.Initialize ();
Initializes a STATIONARITY object to an empty state. This method must be called before the time series array and other attributes are specified for the STATIONARITY object.
Arguments
There are no arguments associated with this method.
STATIONARITY.SetY Method
rc=obj.SetY (YSeries);
Specifies the time series array (YSeries) for the STATIONARITY object.
Input Arguments
You must specify the following input argument:
- YSeries
specifies a numeric array that contains the time series for the STATIONARITY object to analyze.
STATIONARITY.SetOption Method
rc=obj.SetOption ('Name',Value <,'Name',Value, …> );
Sets a named option for the STATIONARITY object.
Input Arguments
You must specify at least one of the following for 'Name' and its associated Value:
- 'METHOD'
-
takes a string Value that specifies the stationarity test method, which can be the augmented Dickey-Fuller (ADF) test, Phillips-Perron (PP) test, or random-walk-with-drift (RW) test. You can specify one of the following Values:
- ADF | Dickey-Fuller
specifies the augmented Dickey-Fuller test.
- PP | Phillips-Perron
specifies the Phillips-Perron test.
- RW | Random-Walk
specifies the random-walk-with-drift test.
The default is ADF.
- 'ORDER' | 'DLAG'
-
takes an integer Value that specifies lags for the stationarity test method.
The Value must be a positive integer between 1 and 12 (inclusive), denoting the order that the STATIONARITY object uses for the test methods. If the value is between 2 and 12 (inclusive) and the method is ADF, the seasonal ADF test is performed. If the value is 1 and the method is ADF, the nonseasonal ADF test is performed. For the PP or RW method, values between 2 and 12 (inclusive) are discarded and the default order of 1 is used.
The default value is 1.
STATIONARITY.SetLags Method
rc=obj.SetLags (Value);
Sets the lags that the STATIONARITY object uses in the stationarity test calculation.
Input Arguments
You must specify the following input argument:
- Value
-
specifies the number of lags to use in the calculation. The allowable value type is an array or a numeric scalar. Specifying a scalar Value is equivalent to specifying an array that contains consecutive numbers from 0 to Value (inclusive).
The default value is 2, which is equivalent to an array {0, 1, 2}.
STATIONARITY.SetDiff Method
rc=obj.SetDiff (Value);
Sets a differencing option for the STATIONARITY object.
Input Arguments
You must specify the following input argument:
- Value
-
specifies a nonnegative integer scalar or an array of nonnegative integers. The STATIONARITY object differences the time series for each integer value in succession prior to performing the test calculations. For example, if you specify the array {1, 3}, then the object first takes the first-order difference and then applies a third-order difference to that first-order-differenced series.
The default value is 0.
STATIONARITY.Run Method
rc=obj.Run ();
Runs the STATIONARITY object to perform various stationarity test calculations by using the time series array that you specify in the SetY method according to the options that you specify in other setter methods, such as SetOption. Upon successful completion, you can extract various results from the OUTSTATIONARITY object.