TD_GOLDFELD_QUANDT 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
Table containing a multivariate series. The SERIES_SPEC is required to have a payload content of MULTIVAR_REAL. The passed-in payload fields must have the following elements and be passed in the order:
  1. Original dependent Y1 field
  2. Field 2, … , fieldN that are the original explanatory variable columns x1, x2, … xN-1.

See Series Specifications.

FUNC_PARAMS
Name Data Type Description
CONST_TERM INTEGER Indicator of whether the regression performed should use a Y-intercept coefficient.
  • A value of 1 means the regression is performed on "Y=C+aX1+bX2+…".
  • A value of 0 means the regression is performed on "Y=aX1+bX2+…".

The default is 1.

START_IDX FLOAT [Optional] The split-point index for the function.
  • If it is less than 1.0, then the split-point index is calculated value times the total number of sample points.
  • If it is greater than 1, then START_IDX is the split-point index.

If not present, then the default for START_IDX is calculated as the (total entries in series minus the OMIT value) divided by 2.

OMIT FLOAT The number of central sample values to omit when forming the two test groups. If less than 1.0, then the number of samples to be omitted is calculated as OMIT times the total number of sample points. If greater than 1, then OMIT is interpreted as number of central points to omit.
SIGNIFICANCE_LEVEL FLOAT The significance level for the test.
TEST String [Optional] TEST influences how Goldfeld-Quandt test statistic is computed and how hypothesis is evaluated. Options are as follows:
  • GREATER: If the Goldfeld-Quandt test-statistic is less than the higher critical value, the null hypothesis is accepted, and there is no evidence of heteroscedastic variance. If the Goldfeld-Quandt test statistic is greater than or equal to the critical value, then the null hypothesis is rejected, and there is evidence of heteroscedastic variance.
  • LESS: If the Goldfeld-Quandt test-statistic is greater than the lower critical value, the null hypothesis is accepted, and there is no evidence of heteroscedastic variance. If the Goldfeld-Quandt test statistic is less than or equal to than the critical value, then the null hypothesis is rejected, and there is evidence of heteroscedastic variance.
  • TWOSIDED: If the Goldfeld-Quandt test-statistic is greater than the lower tail critical value and less than the higher tail critical value, the null hypothesis is accepted, and there is no evidence of heteroscedastic variance. If the Goldfeld-Quandt test statistic is less than or equal to the lower tail critical value or greater than or equal to the high tail critical value, then the null hypothesis is rejected, and there is evidence of heteroscedastic variance.

The default is GREATER.

ALGORITHM VARCHAR(64) Algorithm used for the regression. A value of QR means that QR decomposition is used for the regression. A value of PSI means that pseudo-inverse based on SVD is used to solve the regression.

The default is QR.

INPUT_FMT
No INPUT_FMT options are available for this function.
OUTPUT_FMT
No OUTPUT_FMT options are available for this function.