TC_PACF 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
A time series or spatial series. Series can be REAL or MULTIVAR_REAL.This function accepts a single input source containing univariate series instances or multivariate series instances. The result is univariate or multivariate, respectively.

See Series Specifications.

ART_SPEC
A single input source analytical result table (ART) produced by the TD_ACF function. The ART contains previously-computed auto-correlation coefficients for lag and magnitude. The passed-in TD_ACF result series can be univariate or multivariate, and the result of the TD_PACF operation is univariate or multivariate, respectively. The ART_SPEC is required to have the parameter TABLE_NAME. Do not use any other ART_SPEC parameters.
ART_SPEC( TABLE_NAME( [database-name .] table-name ))

See ART Specifications.

FUNC_PARAMS
Name Data Type Description
INPUT_TYPE Enum, String [Optional] Type of data in the series. Options are:
  • DATA_SERIES: A one dimensional input array that contains a time series or a spatial series.
  • ACF: A one dimensional input array that is indexed by LAG values, and contains previously-generated ACF magnitudes.
Default is DATA_SERIES.
ALGORITHM Enum, String Algorithm to generate the the partial auto-correlation function (PACF) coefficients. Algorithms are Levinson_Durbin and OLS.
MAXLAGS Integer [Optional] Maximum number of lags to calculate the partial autocorrelation.The lag value is limited to one less than the number of observations in the series. If the specified lag value exceeds the limit, the value is replaced with the system-defined maximum value. Number is positive integer. Default is 10*log10(N) where N is the number of observations.
UNBIASED Integer [Optional] The formula to calculate the autocorrelation intermediate values. If 0, then denominator for autocorrelation calculation uses the Jenkins & Watts formula. If 1, then denominator for autocorrelation calculation uses the Box & Jenkins formula. Default is 0.

Only valid when INPUT_TYPE is DATA_SERIES.

ALPHA FLOAT [Optional] Confidence intervals for the given level. For example, if 0.05 is entered, then 95% confidence intervals are returned for standard deviation computed according to Bartlett’s formula.
INPUT_FMT
No INPUT_FMT options are available for this function.
OUTPUT_FMT
No OUTPUT_FMT options are available for this function.