7.00.02 - Arima Arguments - Aster Analytics

Teradata Aster® Analytics Foundation User GuideUpdate 2

Product
Aster Analytics
Release Number
7.00.02
Release Date
September 2017
Content Type
Programming Reference
User Guide
Publication ID
B700-1022-700K
Language
English (United States)
InputTable
Specifies the name of the table or view that contains the input parameters.
ModelTable
Specifies the name of the table where the function outputs the coefficients of the input parameters; that is, the model.
ResidualTable
[Optional] Specify this argument if you will input the model to the ArimaPredictor function.

Specifies the name of the table where the function outputs the residuals of the input parameters.

TimestampColumns
Specifies the names of the input_table columns that specify the sequence (time points) of the input parameters. The sequence must have uniform intervals.
ValueColumn
Specifies the name of the column that contains the time series data in input_table.
Orders
Specifies the values of the nonseasonal parameters p, d, and q for the ARIMA model. Each value must be an INT between 0 and 20, inclusive.
SeasonalOrders
[Optional] Specifies the values of the seasonal parameters sp, sd, and sq for the ARIMA model. Each value must be an INT between 0 and 20, inclusive.
If you specify SeasonalOrders, you must also specify Period.
Period
[Optional] Specifies the period of a season (m in the formula). The period must be a positive integer value.
IncludeMean
[Optional] Specifies whether the function adds the mean value (c in the formula) to the ARIMA model. Default: 'false'.
If IncludeMean is 'true', both d in Orders and sd in SeasonalOrders must be 0.
Fixed
[Optional] Specifies the values of the parameters. The numeric vector fixed_params must have a value for each parameter (for the correspondence between values and parameters, see the note that follows this table). If you specify IncludeMean('true'), you must add the mean value to the end of fixed_params.

If a value in fixed_params is non-NaN, the corresponding parameter is fixed at that value; otherwise, the function optimizes the value of that parameter.

InitValues
[Optional] Specifies the initial values of the parameters. The numeric vector init_params must have a value for each parameter (for the correspondence between values and parameters, see the note that follows this table). If you specify IncludeMean('true'), you must add the initial mean value to the end of init_params.

If a value is NaN, the corresponding parameter has the initial value 0.

MaxIterNum
[Optional] Specifies the maximum iteration number for estimating the parameters. This value must be a positive integer. Default: 100.
The values in the vectors fixed_params and init_params correspond to these parameters in this order:

φ 1, φ 2, … , φ p , θ 1, θ 2, … , θ p , seasonalφ 1, seasonalφ 2, … , seasonalφ sp ,

seasonalθ 1, seasonalθ 2, … , seasonalθ sq , [meanValue]