TD_​DURBIN_​WATSON

It is a test which looks for the presence of serial correlation amongst the error/residual terms. It is mainly employed to analyze the residuals produced by a univariate or multivariate regression (cross-sectional data sets). With respect to regression models, it is expected that there would exist no serial correlation amongst the error terms in contrast, with time series, the expectation is that most likely their will exist serial correlation amongst the error terms.

Options

EXPLANATORY_COUNT

Positive Integer value. The number of explanatory variables in the original regression. The number of explanatory variables plus the INCLUDE_CONSTANT information is needed to perform the lookup in the DW tables.

INCLUDE_CONSTANT

Flag indicating whether the original regression equation contained a 'constant' (an 'intercept'). A value of '0' indicates that no constant was present. A value of '1' indicates that a constant was present. Default is 0.

METHOD

Enumerated value specifying the formula the data scientist wishes to use to calculate the DW test statistic value. A value of 'DW_FORMULA' means use the full summation formula to calculate the value. A value of ACR_LAG1, means execute the regression, 'μt = ρ (μt-1) + νt '; where 'ρ' is the estimate of the autocorrelation at lag 1, and serves the role of the DW statistic.

SIGNIFICANCE_LEVEL

The desired significance level for the test: 0.01, 0.05, etc

Output Schema

Output Schema, if Volatile is true then use user login as the schema.

Output Table

Output Table

VAL Location

VAL Location

Volatile

Specifies whether the table should be a VOLATILE table. If true, then the table is automatically deleted, otherwise it is users responsibility to remove or clean it up for space.

Nodes

• String Configuration5 ×
• Python Script2 ×
• Boolean Configuration1 ×
• Component Input1 ×
• Component Output1 ×
• Show all 13 nodes

Extensions

• FeatureKNIME Base nodes
• FeatureKNIME Database
• FeatureKNIME Quick Forms

Links

• No links available