TD_AUTOARIMA Syntax Elements | Unbounded Array Framework | Teradata Vantage - TD_AUTOARIMA Syntax Elements - Teradata Vantage

Database Unbounded Array Framework Time Series Functions

Deployment
VantageCloud
VantageCore
Edition
Enterprise
IntelliFlex
VMware
Product
Teradata Vantage
Release Number
17.20
Published
June 2022
Language
English (United States)
Last Update
2024-10-04
dita:mapPath
ncd1634149624743.ditamap
dita:ditavalPath
ruu1634160136230.ditaval
dita:id
ncd1634149624743
SERIES_SPEC
Specify the SERIES_SPEC of the input time series.

See Series Specifications.

FUNC_PARAMS
Name Data Type Description
MAX_PQ_NONSEASONAL Integer list [Optional] The (p,q) order of the maximum autoregression (AR) and moving average (MA) parameters. Default is (5, 5).
MAX_PQ_SEASONAL Integer list [Optional] The (P,Q) order of the max seasonal AR and MA parameters. Default is (2,2)
START_PQ_NONSEASONAL Integer list [Optional] The start value of (p,q). Only used when STEPWISE(1). Default is (0, 0).
START_PQ _SEASONAL Integer list [Optional] The start value of seasonal (P,Q). Only used when STEPWISE(1). Default is (0, 0).
d Integer [Optional] The order of first-differencing. Default is -1 (auto search d).
Ds Integer [Optional] The order of seasonal-differencing. Default: -1 (auto search Ds).
MAX_d Integer [Optional] Maximum number of non-seasonal differences. Default is 2.
MAX_Ds Integer [Optional] Maximum number of seasonal differences. Default is 1.
PERIOD Integer [Optional] The number of periods per season. For non-seasonal data, period is 1. Default is 1.
STATIONARY Integer [Optional] If true, the the function restricts search to stationary models. A value of 1 means true. A value of 0 means false. Default is 0.
SEASONAL Integer [Optional] If false, then the function restricts search to non-seasonal models. A value of 1 means true. A value of 0 means false. Default is 1, meaning search all models including seasonal.
CONSTANT Integer [Optional] Indicator that TD_AUTOARIMA function include an intercept. A value of 1 means CONSTANT/intercept must be included. A value of 0 means CONSTANT/intercept must not be included. Default is 1.
ALGORITHM Enumerated list [Optional] The approach used by TD_AUTOARIMA to estimate the coefficients.
  • ALGORITHM (MLE): Use maximum likelihood approach.
  • ALGORITHM (CSS_MLE): Use the conditional sum-of-squares to determine a start value and then do maximum likelihood.
  • ALGORITHM (CSS): Use the conditional sum-ofsquares approach..

Default is ALGORITHM (MLE).

FIT_PERCENTAGE Integer [Optional] Percentage of passed-in sample points used for the model fitting (parameter estimation). The default is 100, meaning 100%.
INFOR_CRITERIA Enumerated list [Optional] Information criterion to be used in model selection. Options are AIC, AICc, BIC. Default is AIC.
STEPWISE Integer [Optional] If true, then the function does stepwise selection. If false, the the function selects all models. A value of 1 means true. A value of 0 means false. Default is 0.
NMODELS Integer Maximum number of models considered in the stepwise search. Default is 94.
MAX_ITERATIONS Integer [Optional] The maximum number of iterations that can be employed to non-linear optimization procedure. Default is 100.
COEFF_STATS Integer [Optional] Indicator to return coefficient statistical columns TSTAT_VALUE and TSTAT_PROB. A value of 1 means return the columns. A value of 0 means do not return the columns. Default is 0.
FIT_METRICS Integer [Optional] Indicator to generate the secondary result set that contains the model metadata statistics. A value of 1 means generate the secondary result set. A value of 0 means do not generate the secondary result set. Default is 0.

The generated result set is retrieved by issuing a TD_EXTRACT_RESULTS against the analytical result table containing the results.

RESIDUAL Integer [Optional] Indicator to generate the tertiary result set that contains the model residuals. A value of 1 means generate the tertiary result set. A value of 0 means do not generate the tertiary result set. Default is 0.

The generated result set is retrieved by issuing a TD_EXTRACT_RESULTS against the analytical result table containing the results.

ARMA_ROOTS Integer [Optional] Indicator to generate the senary result set that contains the inverse AR and MA roots of result best model that TD_AUTOARIMA selected (the model in the primary output layer). There must be no inverse roots showing outside of the unit circle. A value of 1 means generate result set. A value of 0 means do not generate a result set.Default is 0.

The generated result set is retrieved by issuing a TD_EXTRACT_RESULTS against the analytical result table containing the results.

TEST_NONSEASONAL Integer [Optional] Nonseasonal unit root test used to choose differencing number d. Default is ADF.
TD_AUTOARIMA function only uses ADF test for nonseasonal unit root test.
TEST_SEASONAL Integer [Optional] Seasonal unit root test used to choose differencing number D. Default is OCSB.
TD_AUTOARIMA function only uses OCSB test for seasonal unit root test.