importOptions={fileType="ANY" | "AUDIO" | "AUTO" | "BASESAS" | "CSV" | "DELIMITED" | "DOCUMENT" | "DTA" | "ESP" | "EXCEL" | "FMT" | "HDAT" | "IMAGE" | "JMP" | "LASR" | "PARQUET" | "SOUND" | "SPSS" | "VIDEO" | "XLS", fileType-specific-parameters},

name="table-name",

onDemand=TRUE | FALSE,

orderBy

={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

singlePass=TRUE | FALSE,

vars

={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

where="where-expression",

whereTable

casLib="string"

dataSourceOptions={adls_noreq-parameters | bigquery-parameters | cas_noreq-parameters | clouddex-parameters | db2-parameters | dnfs-parameters | esp-parameters | fedsvr-parameters | gcs_noreq-parameters | hadoop-parameters | hana-parameters | impala-parameters | jdbc-parameters | mongodb-parameters | mysql-parameters | odbc-parameters | oracle-parameters | path-parameters | postgres-parameters | redshift-parameters | s3-parameters | sapiq-parameters | sforce-parameters | singlestore_standard-parameters | snowflake-parameters | spark-parameters | spde-parameters | sqlserver-parameters | ss_noreq-parameters | teradata-parameters | vertica-parameters | yellowbrick-parameters}

name="table-name"

vars

={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

}

tolerance=double,

unbiased=TRUE | FALSE,

varsToArgumentsMap={integer-1 <, integer-2, ...>},

weight="variable-name"

;

indicates a required parameter

Summary: Input and Output Tables

If a row includes a subparameter, you can specify the name, caslib, and so on in the subparameter. Otherwise, you can specify the name, caslib, and so on in the parameter.

Parameters for Reading Input Tables
Parameter	Subparameter	Description
required parametertable	—	specifies the table name, caslib, and other common parameters.

Parameters for Creating Output Tables
Parameter	Subparameter	Description
casOutStats	—	specifies the settings for an output table.

Parameter Descriptions

casOutStats={casouttable}

specifies the settings for an output table.

For more information about specifying the casOutStats parameter, see the common casouttable parameter.

Alias	casOut

complementaryStats=TRUE | FALSE

when set to True, complementary univariate statistics such as uncorrected and corrected sum of squared, and coefficient of variation are computed.

Default	FALSE

confidenceInterval=TRUE | FALSE

when set to True, confidence intervals are included in the results. This parameter enables the stdErr parameter.

Default	FALSE

excessKurtosis=TRUE | FALSE

when set to True, excess kurtosis values, instead of kurtosis values, are computed. The excess kurtosis is defined with respect to the normal distribution.

Default	TRUE

freq="variable-name"

specifies the frequency variable.

Alias	frequency

includeMissingGroup=TRUE | FALSE

when set to True, missing values are allowed as group-by keys.

Default	FALSE

inputs={{casinvardesc-1} <, {casinvardesc-2}, ...>}

specifies the variables to use for the analysis. You can specify a subset of the variables from the input table.

For more information about specifying the inputs parameter, see the common casinvardesc parameter.

Alias	vars

maxIterations=integer

specifies the maximum number of iterations for the iterative robust univariate statistics such as MAD scale, GINI scale, and Medcouple skewness estimates. This parameter can be used if the ZSCORE outlier definition is used.

Aliases	maxIters
Aliases	rustatsMaxNiters

nArgumentsForEachVar={integer-1 <, integer-2, ...>}

specifies the number of arguments (request packages) for each variable. If not set, then all request packages are included for all variables.

Alias	nArgsForEachVar

nNominalVars=integer

specifies to treat the last nNomVars variables as nominal if you do not provide a value for the nomVarsIndices parameter.

Minimum value (exclusive)	0

nominalStats={nominalStatistics}

computes nominal statistics. These include indices of qualitative variation and most and least frequent values.

The nominalStatistics value can be one or more of the following:

bottomK=integer

specifies the number of least frequent items to compute.

Default	5

distinctCountLimit=integer

specifies the distinct count limit.

fuzzyCompare=double

specifies the fuzzy comparison threshold that is used to determine distinctness of numeric values.

Alias	precision
Range	0–1E-05

iqv=TRUE | FALSE

when set to True, computes indices of qualitative variation. These include Shannon entropy, Gini index and a few other frequency distribution dispersion measures.

Default	TRUE

topK=integer

specifies the number of most frequent items to compute.

Default	5

nominalVarsIndices={integer-1 <, integer-2, ...>}

specifies the indices of the variables to treat as nominal variables.

outputTableOptions={outputTableOptions}

specifies options for result tables. You can specify which result tables the server returns and how group-by results are handled.

Alias	outputTableOpts

The outputTableOptions value can be one or more of the following:

forceTableReturn=TRUE | FALSE

when set to True, result tables are returned to the client even if the output is also saved as an output table.

Default	FALSE

tableNames={"string-1" <, "string-2", ...>}

specifies the names of result tables to generate. By default, all result tables are returned.

Alias	outputTables

percentileDefinition=integer

specifies the percentile definition to use. The definitions are numbered 1 to 6. The default value is 6.

Alias	pctlDef
Default	6
Range	1–6

percentileMaxIterations=integer

specifies the maximum number of iterations for percentile computation.

Alias	pctlMaxIters

percentileTolerance=double

specifies the tolerance for percentile computation.

Alias	pctlEpsilon
Default	1E-05

quantileSketch={quantileSketchOptions}

specifies the options for quantile sketch.

Alias	quantileSketchOptions

The quantileSketchOptions value can be one or more of the following:

compressionFactor=double

specifies the compression factor to use for quantile sketch.

Default	10
Minimum value	1

epsilon=double

specifies the tolerance to use for quantile sketch.

Default	0.001
Range	1E-06–0.1

requestPackages={{rustatsRequestPackage-1} <, {rustatsRequestPackage-2}, ...>}

specifies an array of robust univariate statistics request packages to be processed by the action.

Alias	reqPacks

The rustatsRequestPackage value can be one or more of the following:

aadLocationUseMean=TRUE | FALSE

when set to True, the mean is used, instead of the median, as the center for the absolute average deviation (AAD) scale estimator.

Alias	aadLocUseMean
Default	TRUE

allCentralizedMoments=TRUE | FALSE

when set to True, computes all centralized moments (up to the sixth order).

Default	FALSE

allKurtoses=TRUE | FALSE

when set to True, computes all kurtosis estimates.

Default	FALSE

allLocations=TRUE | FALSE

when set to True, computes all location estimates.

Default	FALSE

allNominalStats=TRUE | FALSE

computes all nominal statistics. These include indices of qualitative variation and most and least frequent values.

Default	FALSE

allScales=TRUE | FALSE

when set to True, computes all scale estimates.

Default	FALSE

allSkewnesses=TRUE | FALSE

when set to True, computes all skewness estimates.

Default	FALSE

alpha=double

specifies the significance level for the confidence interval of location estimates.

Default	0.05

kurtoses={"AVGQUANTILE", "CLASSICAL", "MOORS", "QUANTILE"} | {"string-1" <, "string-2", ...>}

specifies a list of the kurtosis estimate types to compute.

AVGQUANTILE	uses averaged quantile based skewness estimate.
CLASSICAL	uses the classical kurtosis estimate.
MOORS	uses Moor kurtosis estimate.
QUANTILE	uses quantile based kurtosis estimate.

kurtosisAlphaQuantile=double

specifies the lower (alpha) quantile for quantile or the average quantile kurtosis estimator.

Alias	kurtAlphaQuantile
Default	2.5
Range	(0–50]

kurtosisBetaQuantile=double

specifies the upper (beta) quantile for quantile or the average quantile kurtosis estimator.

Alias	kurtBetaQuantile
Default	25
Range	(0–50]

locationBiweightTuning=double

specifies the tuning factor for the Tukey biweight location estimator.

Alias	locBiweightTuning
Default	6
Minimum value (exclusive)	0

locationLowerPercentile=double

specifies the lower percentile for location estimates that need a percentile.

Alias	locLowerPerc
Default	5
Range	(0, 50)

locations={"BIWEIGHT", "GEOMETRICMEAN", "HARMONICMEAN", "MEAN", "MEDIAN", "TRIMMEDMEAN", "WINSORIZEDMEAN"} | {"string-1" <, "string-2", ...>}

specifies a list of the location estimate types to compute.

BIWEIGHT	uses Tukey biweight based estimate for location.
GEOMETRICMEAN	uses the geometric mean for location.
HARMONICMEAN	uses the harmonic mean for location.
MEAN	uses the arithmetic mean for location.
MEDIAN	uses the median value for location.
TRIMMEDMEAN	uses the trimmed mean for location. You can specify bounds with the lowerPerc, upperPerc, or symPerc parameters.
WINSORIZEDMEAN	uses the Winsorized mean for location. You can specify bounds with the lowerPerc, upperPerc, or symPerc parameters.

locationSymmetricPercentile=double

specifies the symmetric percentile for the location estimates that need percentiles. For example, a value of 20 indicates to set a lower percentile to 10 and the upper percentile to 90.

Alias	locSymPerc
Default	10
Range	(0, 100)

locationUpperPercentile=double

specifies the upper percentile for location estimates that need a percentile.

Alias	locUpperPerc
Default	95
Range	(50, 100)

maxOrder=integer

specifies the maximum order of the centralized moment to compute.

Alias	nMoments
Default	4
Maximum value	6

nPercentiles=integer

computes the equal frequency percentiles. For example, setting the value to 3 asks for the computation of 25, 50, and 75 percentiles.

Default	0
Minimum value	0

percentiles={double-1 <, double-2, ...>}

specifies a list of quantiles or percentiles to compute.

scaleBiweightTuning=double

specifies the tuning factor for the Tukey biweight scale estimator.

Alias	sclBiweightTuning
Default	9
Minimum value (exclusive)	0

scales={"AAD", "BIWEIGHT", "GINI", "IQR", "MAD", "STD"} | {"string-1" <, "string-2", ...>}

specifies a list of the scale estimate types to compute.

AAD	uses the absolute deviation about the mean or median as scale.
BIWEIGHT	uses Tukey biweight based estimate for scale.
GINI	uses the Gini scale for scale.
IQR	uses the inter-quartile range for scale.
MAD	uses the median absolute deviation about the median for scale.
STD	uses the standard deviation for scale.

skewnesses={"AVGQUANTILE", "CLASSICAL", "PEARMED", "QUANTILE"} | {"string-1" <, "string-2", ...>}

specifies a list of the skewness estimate types to compute.

AVGQUANTILE	uses average quantile based skewness estimate.
CLASSICAL	uses the classical skewness coefficient for skewness.
PEARMED	uses Pearson median skewness coefficient for skewness.
QUANTILE	uses quantile based skewness estimate.

skewnessQuantile=double

specifies the quantile for quantile skewness estimator.

Alias	skewQuantile
Default	25
Range	(0, 50)

standardizeMoments=TRUE | FALSE

specifies that standardized moments be generated, instead of the centralized moments.

Alias	stdMoments
Default	FALSE

seed=integer

specifies a seed value. The seed is used to generate random values.

Default	0

standardError=TRUE | FALSE

when set to True, standard errors for location are included in the results.

Alias	stdErr
Default	FALSE

* table={castable}

specifies the table name, caslib, and other common parameters.

For more information about specifying the table parameter, see the common castable parameter.

tolerance=double

specifies the tolerance for the iterative robust univariate statistics.

Default	1E-05

unbiased=TRUE | FALSE

when set to True, the standard deviation, variance, classical skewness and classical kurtosis are corrected for bias.

Default	TRUE

varsToArgumentsMap={integer-1 <, integer-2, ...>}

specifies which request packages to compute for each variable. If a value is specified for the nArgsForEachVar parameter, then you must set this. Otherwise, both parameters are ignored and all request packages are computed for all variables.

weight="variable-name"

specifies the weight variable.

rustats Action

Computes robust univariate statistics, centralized moments, quantiles, and frequency distribution statistics.

Lua Syntax

Expand all Collapse all

results, info = s:dataPreprocess_rustats{

casOutStats

caslib="string",

compress=true | false,

indexVars={"variable-name-1" <, "variable-name-2", ...>},

label="string",

lifetime=64-bit-integer,

maxMemSize=64-bit-integer,

memoryFormat="DVR" | "INHERIT" | "STANDARD",

name="table-name",

onDemand=true | false,

promote=true | false,

replace=true | false,

replication=integer,

threadBlockSize=64-bit-integer,

timeStamp="string",

where={"string-1" <, "string-2", ...>}

complementaryStats=true | false,

confidenceInterval=true | false,

excessKurtosis=true | false,

freq="variable-name",

includeMissingGroup=true | false,

inputs

={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

maxIterations=integer,

nArgumentsForEachVar={integer-1 <, integer-2, ...>},

nNominalVars=integer,

nominalStats

bottomK=integer,

distinctCountLimit=integer,

fuzzyCompare=double,

iqv=true | false,

topK=integer

nominalVarsIndices={integer-1 <, integer-2, ...>},

outputTableOptions

forceTableReturn=true | false,

tableNames={"string-1" <, "string-2", ...>}

percentileDefinition=integer,

percentileMaxIterations=integer,

percentileTolerance=double,

quantileSketch

compressionFactor=double,

epsilon=double

requestPackages

={{

aadLocationUseMean=true | false,

allCentralizedMoments=true | false,

allKurtoses=true | false,

allLocations=true | false,

allNominalStats=true | false,

allScales=true | false,

allSkewnesses=true | false,

alpha=double,

kurtoses={"AVGQUANTILE", "CLASSICAL", "MOORS", "QUANTILE"} | {"string-1" <, "string-2", ...>},

kurtosisAlphaQuantile=double,

kurtosisBetaQuantile=double,

locationBiweightTuning=double,

locationLowerPercentile=double,

locations={"BIWEIGHT", "GEOMETRICMEAN", "HARMONICMEAN", "MEAN", "MEDIAN", "TRIMMEDMEAN", "WINSORIZEDMEAN"} | {"string-1" <, "string-2", ...>},

locationSymmetricPercentile=double,

locationUpperPercentile=double,

maxOrder=integer,

nPercentiles=integer,

percentiles={double-1 <, double-2, ...>},

scaleBiweightTuning=double,

scales={"AAD", "BIWEIGHT", "GINI", "IQR", "MAD", "STD"} | {"string-1" <, "string-2", ...>},

skewnesses={"AVGQUANTILE", "CLASSICAL", "PEARMED", "QUANTILE"} | {"string-1" <, "string-2", ...>},

skewnessQuantile=double,

standardizeMoments=true | false

}, {...}},

seed=integer,

standardError=true | false,

table

caslib="string",

computedOnDemand=true | false,

computedVars

={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

computedVarsProgram="string",

dataSourceOptions={key-1=any-list-or-data-type-1 <, key-2=any-list-or-data-type-2, ...>},

groupBy

={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

groupByMode="NOSORT" | "REDISTRIBUTE",

name="table-name",

onDemand=true | false,

orderBy

={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

singlePass=true | false,

vars

={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

where="where-expression",

whereTable

casLib="string"

name="table-name"

vars

={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

}

tolerance=double,

unbiased=true | false,

varsToArgumentsMap={integer-1 <, integer-2, ...>},

weight="variable-name"

}

indicates a required parameter

Summary: Input and Output Tables

If a row includes a subparameter, you can specify the name, caslib, and so on in the subparameter. Otherwise, you can specify the name, caslib, and so on in the parameter.

Parameters for Reading Input Tables
Parameter	Subparameter	Description
required parametertable	—	specifies the table name, caslib, and other common parameters.

Parameters for Creating Output Tables
Parameter	Subparameter	Description
casOutStats	—	specifies the settings for an output table.

Parameter Descriptions

casOutStats={casouttable}

specifies the settings for an output table.

For more information about specifying the casOutStats parameter, see the common casouttable parameter.

Alias	casOut

complementaryStats=true | false

when set to True, complementary univariate statistics such as uncorrected and corrected sum of squared, and coefficient of variation are computed.

Default	false

confidenceInterval=true | false

when set to True, confidence intervals are included in the results. This parameter enables the stdErr parameter.

Default	false

excessKurtosis=true | false

when set to True, excess kurtosis values, instead of kurtosis values, are computed. The excess kurtosis is defined with respect to the normal distribution.

Default	true

freq="variable-name"

specifies the frequency variable.

Alias	frequency

includeMissingGroup=true | false

when set to True, missing values are allowed as group-by keys.

Default	false

inputs={{casinvardesc-1} <, {casinvardesc-2}, ...>}

specifies the variables to use for the analysis. You can specify a subset of the variables from the input table.

For more information about specifying the inputs parameter, see the common casinvardesc parameter.

Alias	vars

maxIterations=integer

Aliases	maxIters
Aliases	rustatsMaxNiters

nArgumentsForEachVar={integer-1 <, integer-2, ...>}

specifies the number of arguments (request packages) for each variable. If not set, then all request packages are included for all variables.

Alias	nArgsForEachVar

nNominalVars=integer

specifies to treat the last nNomVars variables as nominal if you do not provide a value for the nomVarsIndices parameter.

Minimum value (exclusive)	0

nominalStats={nominalStatistics}

computes nominal statistics. These include indices of qualitative variation and most and least frequent values.

The nominalStatistics value can be one or more of the following:

bottomK=integer

specifies the number of least frequent items to compute.

Default	5

distinctCountLimit=integer

specifies the distinct count limit.

fuzzyCompare=double

specifies the fuzzy comparison threshold that is used to determine distinctness of numeric values.

Alias	precision
Range	0–1E-05

iqv=true | false

when set to True, computes indices of qualitative variation. These include Shannon entropy, Gini index and a few other frequency distribution dispersion measures.

Default	true

topK=integer

specifies the number of most frequent items to compute.

Default	5

nominalVarsIndices={integer-1 <, integer-2, ...>}

specifies the indices of the variables to treat as nominal variables.

outputTableOptions={outputTableOptions}

specifies options for result tables. You can specify which result tables the server returns and how group-by results are handled.

Alias	outputTableOpts

The outputTableOptions value can be one or more of the following:

forceTableReturn=true | false

when set to True, result tables are returned to the client even if the output is also saved as an output table.

Default	false

tableNames={"string-1" <, "string-2", ...>}

specifies the names of result tables to generate. By default, all result tables are returned.

Alias	outputTables

percentileDefinition=integer

specifies the percentile definition to use. The definitions are numbered 1 to 6. The default value is 6.

Alias	pctlDef
Default	6
Range	1–6

percentileMaxIterations=integer

specifies the maximum number of iterations for percentile computation.

Alias	pctlMaxIters

percentileTolerance=double

specifies the tolerance for percentile computation.

Alias	pctlEpsilon
Default	1E-05

quantileSketch={quantileSketchOptions}

specifies the options for quantile sketch.

Alias	quantileSketchOptions

The quantileSketchOptions value can be one or more of the following:

compressionFactor=double

specifies the compression factor to use for quantile sketch.

Default	10
Minimum value	1

epsilon=double

specifies the tolerance to use for quantile sketch.

Default	0.001
Range	1E-06–0.1

requestPackages={{rustatsRequestPackage-1} <, {rustatsRequestPackage-2}, ...>}

specifies an array of robust univariate statistics request packages to be processed by the action.

Alias	reqPacks

The rustatsRequestPackage value can be one or more of the following:

aadLocationUseMean=true | false

when set to True, the mean is used, instead of the median, as the center for the absolute average deviation (AAD) scale estimator.

Alias	aadLocUseMean
Default	true

allCentralizedMoments=true | false

when set to True, computes all centralized moments (up to the sixth order).

Default	false

allKurtoses=true | false

when set to True, computes all kurtosis estimates.

Default	false

allLocations=true | false

when set to True, computes all location estimates.

Default	false

allNominalStats=true | false

computes all nominal statistics. These include indices of qualitative variation and most and least frequent values.

Default	false

allScales=true | false

when set to True, computes all scale estimates.

Default	false

allSkewnesses=true | false

when set to True, computes all skewness estimates.

Default	false

alpha=double

specifies the significance level for the confidence interval of location estimates.

Default	0.05

kurtoses={"AVGQUANTILE", "CLASSICAL", "MOORS", "QUANTILE"} | {"string-1" <, "string-2", ...>}

specifies a list of the kurtosis estimate types to compute.

AVGQUANTILE	uses averaged quantile based skewness estimate.
CLASSICAL	uses the classical kurtosis estimate.
MOORS	uses Moor kurtosis estimate.
QUANTILE	uses quantile based kurtosis estimate.

kurtosisAlphaQuantile=double

specifies the lower (alpha) quantile for quantile or the average quantile kurtosis estimator.

Alias	kurtAlphaQuantile
Default	2.5
Range	(0–50]

kurtosisBetaQuantile=double

specifies the upper (beta) quantile for quantile or the average quantile kurtosis estimator.

Alias	kurtBetaQuantile
Default	25
Range	(0–50]

locationBiweightTuning=double

specifies the tuning factor for the Tukey biweight location estimator.

Alias	locBiweightTuning
Default	6
Minimum value (exclusive)	0

locationLowerPercentile=double

specifies the lower percentile for location estimates that need a percentile.

Alias	locLowerPerc
Default	5
Range	(0, 50)

locations={"BIWEIGHT", "GEOMETRICMEAN", "HARMONICMEAN", "MEAN", "MEDIAN", "TRIMMEDMEAN", "WINSORIZEDMEAN"} | {"string-1" <, "string-2", ...>}

specifies a list of the location estimate types to compute.

BIWEIGHT	uses Tukey biweight based estimate for location.
GEOMETRICMEAN	uses the geometric mean for location.
HARMONICMEAN	uses the harmonic mean for location.
MEAN	uses the arithmetic mean for location.
MEDIAN	uses the median value for location.
TRIMMEDMEAN	uses the trimmed mean for location. You can specify bounds with the lowerPerc, upperPerc, or symPerc parameters.
WINSORIZEDMEAN	uses the Winsorized mean for location. You can specify bounds with the lowerPerc, upperPerc, or symPerc parameters.

locationSymmetricPercentile=double

specifies the symmetric percentile for the location estimates that need percentiles. For example, a value of 20 indicates to set a lower percentile to 10 and the upper percentile to 90.

Alias	locSymPerc
Default	10
Range	(0, 100)

locationUpperPercentile=double

specifies the upper percentile for location estimates that need a percentile.

Alias	locUpperPerc
Default	95
Range	(50, 100)

maxOrder=integer

specifies the maximum order of the centralized moment to compute.

Alias	nMoments
Default	4
Maximum value	6

nPercentiles=integer

computes the equal frequency percentiles. For example, setting the value to 3 asks for the computation of 25, 50, and 75 percentiles.

Default	0
Minimum value	0

percentiles={double-1 <, double-2, ...>}

specifies a list of quantiles or percentiles to compute.

scaleBiweightTuning=double

specifies the tuning factor for the Tukey biweight scale estimator.

Alias	sclBiweightTuning
Default	9
Minimum value (exclusive)	0

scales={"AAD", "BIWEIGHT", "GINI", "IQR", "MAD", "STD"} | {"string-1" <, "string-2", ...>}

specifies a list of the scale estimate types to compute.

AAD	uses the absolute deviation about the mean or median as scale.
BIWEIGHT	uses Tukey biweight based estimate for scale.
GINI	uses the Gini scale for scale.
IQR	uses the inter-quartile range for scale.
MAD	uses the median absolute deviation about the median for scale.
STD	uses the standard deviation for scale.

skewnesses={"AVGQUANTILE", "CLASSICAL", "PEARMED", "QUANTILE"} | {"string-1" <, "string-2", ...>}

specifies a list of the skewness estimate types to compute.

AVGQUANTILE	uses average quantile based skewness estimate.
CLASSICAL	uses the classical skewness coefficient for skewness.
PEARMED	uses Pearson median skewness coefficient for skewness.
QUANTILE	uses quantile based skewness estimate.

skewnessQuantile=double

specifies the quantile for quantile skewness estimator.

Alias	skewQuantile
Default	25
Range	(0, 50)

standardizeMoments=true | false

specifies that standardized moments be generated, instead of the centralized moments.

Alias	stdMoments
Default	false

seed=integer

specifies a seed value. The seed is used to generate random values.

Default	0

standardError=true | false

when set to True, standard errors for location are included in the results.

Alias	stdErr
Default	false

* table={castable}

specifies the table name, caslib, and other common parameters.

For more information about specifying the table parameter, see the common castable parameter.

tolerance=double

specifies the tolerance for the iterative robust univariate statistics.

Default	1E-05

unbiased=true | false

when set to True, the standard deviation, variance, classical skewness and classical kurtosis are corrected for bias.

Default	true

varsToArgumentsMap={integer-1 <, integer-2, ...>}

weight="variable-name"

specifies the weight variable.

rustats Action

Computes robust univariate statistics, centralized moments, quantiles, and frequency distribution statistics.

Python Syntax

Expand all Collapse all

results=s.dataPreprocess.rustats(

casOutStats

"caslib":"string",

"compress":True | False,

"indexVars":["variable-name-1" <, "variable-name-2", ...>],

"label":"string",

"lifetime":64-bit-integer,

"maxMemSize":64-bit-integer,

"memoryFormat":"DVR" | "INHERIT" | "STANDARD",

"name":"table-name",

"onDemand":True | False,

"promote":True | False,

"replace":True | False,

"replication":integer,

"threadBlockSize":64-bit-integer,

"timeStamp":"string",

"where":["string-1" <, "string-2", ...>]

complementaryStats=True | False,

confidenceInterval=True | False,

excessKurtosis=True | False,

freq="variable-name",

includeMissingGroup=True | False,

inputs

=[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>],

maxIterations=integer,

nArgumentsForEachVar=[integer-1 <, integer-2, ...>],

nNominalVars=integer,

nominalStats

"bottomK":integer,

"distinctCountLimit":integer,

"fuzzyCompare":double,

"iqv":True | False,

"topK":integer

nominalVarsIndices=[integer-1 <, integer-2, ...>],

outputTableOptions

"forceTableReturn":True | False,

"tableNames":["string-1" <, "string-2", ...>]

percentileDefinition=integer,

percentileMaxIterations=integer,

percentileTolerance=double,

quantileSketch

"compressionFactor":double,

"epsilon":double

requestPackages

=[{

"aadLocationUseMean":True | False,

"allCentralizedMoments":True | False,

"allKurtoses":True | False,

"allLocations":True | False,

"allNominalStats":True | False,

"allScales":True | False,

"allSkewnesses":True | False,

"alpha":double,

"kurtoses":["AVGQUANTILE", "CLASSICAL", "MOORS", "QUANTILE"] | ["string-1" <, "string-2", ...>],

"kurtosisAlphaQuantile":double,

"kurtosisBetaQuantile":double,

"locationBiweightTuning":double,

"locationLowerPercentile":double,

"locations":["BIWEIGHT", "GEOMETRICMEAN", "HARMONICMEAN", "MEAN", "MEDIAN", "TRIMMEDMEAN", "WINSORIZEDMEAN"] | ["string-1" <, "string-2", ...>],

"locationSymmetricPercentile":double,

"locationUpperPercentile":double,

"maxOrder":integer,

"nPercentiles":integer,

"percentiles":[double-1 <, double-2, ...>],

"scaleBiweightTuning":double,

"scales":["AAD", "BIWEIGHT", "GINI", "IQR", "MAD", "STD"] | ["string-1" <, "string-2", ...>],

"skewnesses":["AVGQUANTILE", "CLASSICAL", "PEARMED", "QUANTILE"] | ["string-1" <, "string-2", ...>],

"skewnessQuantile":double,

"standardizeMoments":True | False

}<, {...}>],

seed=integer,

standardError=True | False,

table

"caslib":"string",

"computedOnDemand":True | False,

"computedVars"

:[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>],

"computedVarsProgram":"string",

"dataSourceOptions":{"key-1":{any-list-or-data-type-1} <, "key-2":{any-list-or-data-type-2}, ...>},

"groupBy"

:[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>],

"groupByMode":"NOSORT" | "REDISTRIBUTE",

"importOptions":{"fileType":"ANY" | "AUDIO" | "AUTO" | "BASESAS" | "CSV" | "DELIMITED" | "DOCUMENT" | "DTA" | "ESP" | "EXCEL" | "FMT" | "HDAT" | "IMAGE" | "JMP" | "LASR" | "PARQUET" | "SOUND" | "SPSS" | "VIDEO" | "XLS", fileType-specific-parameters},

"name":"table-name",

"onDemand":True | False,

"orderBy"

:[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>],

"singlePass":True | False,

"vars"

:[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>],

"where":"where-expression",

"whereTable"

"casLib":"string"

"dataSourceOptions":{adls_noreq-parameters | bigquery-parameters | cas_noreq-parameters | clouddex-parameters | db2-parameters | dnfs-parameters | esp-parameters | fedsvr-parameters | gcs_noreq-parameters | hadoop-parameters | hana-parameters | impala-parameters | jdbc-parameters | mongodb-parameters | mysql-parameters | odbc-parameters | oracle-parameters | path-parameters | postgres-parameters | redshift-parameters | s3-parameters | sapiq-parameters | sforce-parameters | singlestore_standard-parameters | snowflake-parameters | spark-parameters | spde-parameters | sqlserver-parameters | ss_noreq-parameters | teradata-parameters | vertica-parameters | yellowbrick-parameters}

"name":"table-name"

"vars"

:[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"where":"where-expression"

}

tolerance=double,

unbiased=True | False,

varsToArgumentsMap=[integer-1 <, integer-2, ...>],

weight="variable-name"

)

indicates a required parameter

Summary: Input and Output Tables

If a row includes a subparameter, you can specify the name, caslib, and so on in the subparameter. Otherwise, you can specify the name, caslib, and so on in the parameter.

Parameters for Reading Input Tables
Parameter	Subparameter	Description
required parametertable	—	specifies the table name, caslib, and other common parameters.

Parameters for Creating Output Tables
Parameter	Subparameter	Description
casOutStats	—	specifies the settings for an output table.

Parameter Descriptions

casOutStats={casouttable}

specifies the settings for an output table.

For more information about specifying the casOutStats parameter, see the common casouttable parameter.

Alias	casOut

complementaryStats=True | False

when set to True, complementary univariate statistics such as uncorrected and corrected sum of squared, and coefficient of variation are computed.

Default	False

confidenceInterval=True | False

when set to True, confidence intervals are included in the results. This parameter enables the stdErr parameter.

Default	False

excessKurtosis=True | False

when set to True, excess kurtosis values, instead of kurtosis values, are computed. The excess kurtosis is defined with respect to the normal distribution.

Default	True

freq="variable-name"

specifies the frequency variable.

Alias	frequency

includeMissingGroup=True | False

when set to True, missing values are allowed as group-by keys.

Default	False

inputs=[{casinvardesc-1} <, {casinvardesc-2}, ...>]

specifies the variables to use for the analysis. You can specify a subset of the variables from the input table.

For more information about specifying the inputs parameter, see the common casinvardesc parameter.

Alias	vars

maxIterations=integer

Aliases	maxIters
Aliases	rustatsMaxNiters

nArgumentsForEachVar=[integer-1 <, integer-2, ...>]

specifies the number of arguments (request packages) for each variable. If not set, then all request packages are included for all variables.

Alias	nArgsForEachVar

nNominalVars=integer

specifies to treat the last nNomVars variables as nominal if you do not provide a value for the nomVarsIndices parameter.

Minimum value (exclusive)	0

nominalStats={nominalStatistics}

computes nominal statistics. These include indices of qualitative variation and most and least frequent values.

The nominalStatistics value can be one or more of the following:

"bottomK":integer

specifies the number of least frequent items to compute.

Default	5

"distinctCountLimit":integer

specifies the distinct count limit.

"fuzzyCompare":double

specifies the fuzzy comparison threshold that is used to determine distinctness of numeric values.

Alias	precision
Range	0–1E-05

"iqv":True | False

when set to True, computes indices of qualitative variation. These include Shannon entropy, Gini index and a few other frequency distribution dispersion measures.

Default	True

"topK":integer

specifies the number of most frequent items to compute.

Default	5

nominalVarsIndices=[integer-1 <, integer-2, ...>]

specifies the indices of the variables to treat as nominal variables.

outputTableOptions={outputTableOptions}

specifies options for result tables. You can specify which result tables the server returns and how group-by results are handled.

Alias	outputTableOpts

The outputTableOptions value can be one or more of the following:

"forceTableReturn":True | False

when set to True, result tables are returned to the client even if the output is also saved as an output table.

Default	False

"tableNames":["string-1" <, "string-2", ...>]

specifies the names of result tables to generate. By default, all result tables are returned.

Alias	outputTables

percentileDefinition=integer

specifies the percentile definition to use. The definitions are numbered 1 to 6. The default value is 6.

Alias	pctlDef
Default	6
Range	1–6

percentileMaxIterations=integer

specifies the maximum number of iterations for percentile computation.

Alias	pctlMaxIters

percentileTolerance=double

specifies the tolerance for percentile computation.

Alias	pctlEpsilon
Default	1E-05

quantileSketch={quantileSketchOptions}

specifies the options for quantile sketch.

Alias	quantileSketchOptions

The quantileSketchOptions value can be one or more of the following:

"compressionFactor":double

specifies the compression factor to use for quantile sketch.

Default	10
Minimum value	1

"epsilon":double

specifies the tolerance to use for quantile sketch.

Default	0.001
Range	1E-06–0.1

requestPackages=[{rustatsRequestPackage-1} <, {rustatsRequestPackage-2}, ...>]

specifies an array of robust univariate statistics request packages to be processed by the action.

Alias	reqPacks

The rustatsRequestPackage value can be one or more of the following:

"aadLocationUseMean":True | False

when set to True, the mean is used, instead of the median, as the center for the absolute average deviation (AAD) scale estimator.

Alias	aadLocUseMean
Default	True

"allCentralizedMoments":True | False

when set to True, computes all centralized moments (up to the sixth order).

Default	False

"allKurtoses":True | False

when set to True, computes all kurtosis estimates.

Default	False

"allLocations":True | False

when set to True, computes all location estimates.

Default	False

"allNominalStats":True | False

computes all nominal statistics. These include indices of qualitative variation and most and least frequent values.

Default	False

"allScales":True | False

when set to True, computes all scale estimates.

Default	False

"allSkewnesses":True | False

when set to True, computes all skewness estimates.

Default	False

"alpha":double

specifies the significance level for the confidence interval of location estimates.

Default	0.05

"kurtoses":["AVGQUANTILE", "CLASSICAL", "MOORS", "QUANTILE"] | ["string-1" <, "string-2", ...>]

specifies a list of the kurtosis estimate types to compute.

AVGQUANTILE	uses averaged quantile based skewness estimate.
CLASSICAL	uses the classical kurtosis estimate.
MOORS	uses Moor kurtosis estimate.
QUANTILE	uses quantile based kurtosis estimate.

"kurtosisAlphaQuantile":double

specifies the lower (alpha) quantile for quantile or the average quantile kurtosis estimator.

Alias	kurtAlphaQuantile
Default	2.5
Range	(0–50]

"kurtosisBetaQuantile":double

specifies the upper (beta) quantile for quantile or the average quantile kurtosis estimator.

Alias	kurtBetaQuantile
Default	25
Range	(0–50]

"locationBiweightTuning":double

specifies the tuning factor for the Tukey biweight location estimator.

Alias	locBiweightTuning
Default	6
Minimum value (exclusive)	0

"locationLowerPercentile":double

specifies the lower percentile for location estimates that need a percentile.

Alias	locLowerPerc
Default	5
Range	(0, 50)

"locations":["BIWEIGHT", "GEOMETRICMEAN", "HARMONICMEAN", "MEAN", "MEDIAN", "TRIMMEDMEAN", "WINSORIZEDMEAN"] | ["string-1" <, "string-2", ...>]

specifies a list of the location estimate types to compute.

BIWEIGHT	uses Tukey biweight based estimate for location.
GEOMETRICMEAN	uses the geometric mean for location.
HARMONICMEAN	uses the harmonic mean for location.
MEAN	uses the arithmetic mean for location.
MEDIAN	uses the median value for location.
TRIMMEDMEAN	uses the trimmed mean for location. You can specify bounds with the lowerPerc, upperPerc, or symPerc parameters.
WINSORIZEDMEAN	uses the Winsorized mean for location. You can specify bounds with the lowerPerc, upperPerc, or symPerc parameters.

"locationSymmetricPercentile":double

specifies the symmetric percentile for the location estimates that need percentiles. For example, a value of 20 indicates to set a lower percentile to 10 and the upper percentile to 90.

Alias	locSymPerc
Default	10
Range	(0, 100)

"locationUpperPercentile":double

specifies the upper percentile for location estimates that need a percentile.

Alias	locUpperPerc
Default	95
Range	(50, 100)

"maxOrder":integer

specifies the maximum order of the centralized moment to compute.

Alias	nMoments
Default	4
Maximum value	6

"nPercentiles":integer

computes the equal frequency percentiles. For example, setting the value to 3 asks for the computation of 25, 50, and 75 percentiles.

Default	0
Minimum value	0

"percentiles":[double-1 <, double-2, ...>]

specifies a list of quantiles or percentiles to compute.

"scaleBiweightTuning":double

specifies the tuning factor for the Tukey biweight scale estimator.

Alias	sclBiweightTuning
Default	9
Minimum value (exclusive)	0

"scales":["AAD", "BIWEIGHT", "GINI", "IQR", "MAD", "STD"] | ["string-1" <, "string-2", ...>]

specifies a list of the scale estimate types to compute.

AAD	uses the absolute deviation about the mean or median as scale.
BIWEIGHT	uses Tukey biweight based estimate for scale.
GINI	uses the Gini scale for scale.
IQR	uses the inter-quartile range for scale.
MAD	uses the median absolute deviation about the median for scale.
STD	uses the standard deviation for scale.

"skewnesses":["AVGQUANTILE", "CLASSICAL", "PEARMED", "QUANTILE"] | ["string-1" <, "string-2", ...>]

specifies a list of the skewness estimate types to compute.

AVGQUANTILE	uses average quantile based skewness estimate.
CLASSICAL	uses the classical skewness coefficient for skewness.
PEARMED	uses Pearson median skewness coefficient for skewness.
QUANTILE	uses quantile based skewness estimate.

"skewnessQuantile":double

specifies the quantile for quantile skewness estimator.

Alias	skewQuantile
Default	25
Range	(0, 50)

"standardizeMoments":True | False

specifies that standardized moments be generated, instead of the centralized moments.

Alias	stdMoments
Default	False

seed=integer

specifies a seed value. The seed is used to generate random values.

Default	0

standardError=True | False

when set to True, standard errors for location are included in the results.

Alias	stdErr
Default	False

* table={castable}

specifies the table name, caslib, and other common parameters.

For more information about specifying the table parameter, see the common castable parameter.

tolerance=double

specifies the tolerance for the iterative robust univariate statistics.

Default	1E-05

unbiased=True | False

when set to True, the standard deviation, variance, classical skewness and classical kurtosis are corrected for bias.

Default	True

varsToArgumentsMap=[integer-1 <, integer-2, ...>]

weight="variable-name"

specifies the weight variable.

rustats Action

Computes robust univariate statistics, centralized moments, quantiles, and frequency distribution statistics.

R Syntax

Expand all Collapse all

results <– cas.dataPreprocess.rustats(s,

casOutStats

=list(

caslib="string",

compress=TRUE | FALSE,

indexVars=list("variable-name-1" <, "variable-name-2", ...>),

label="string",

lifetime=64-bit-integer,

maxMemSize=64-bit-integer,

memoryFormat="DVR" | "INHERIT" | "STANDARD",

name="table-name",

onDemand=TRUE | FALSE,

promote=TRUE | FALSE,

replace=TRUE | FALSE,

replication=integer,

threadBlockSize=64-bit-integer,

timeStamp="string",

where=list("string-1" <, "string-2", ...>)

complementaryStats=TRUE | FALSE,

confidenceInterval=TRUE | FALSE,

excessKurtosis=TRUE | FALSE,

freq="variable-name",

includeMissingGroup=TRUE | FALSE,

inputs

=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>),

maxIterations=integer,

nArgumentsForEachVar=list(integer-1 <, integer-2, ...>),

nNominalVars=integer,

nominalStats

=list(

bottomK=integer,

distinctCountLimit=integer,

fuzzyCompare=double,

iqv=TRUE | FALSE,

topK=integer

nominalVarsIndices=list(integer-1 <, integer-2, ...>),

outputTableOptions

=list(

forceTableReturn=TRUE | FALSE,

tableNames=list("string-1" <, "string-2", ...>)

percentileDefinition=integer,

percentileMaxIterations=integer,

percentileTolerance=double,

quantileSketch

=list(

compressionFactor=double,

epsilon=double

requestPackages

=list( list(

aadLocationUseMean=TRUE | FALSE,

allCentralizedMoments=TRUE | FALSE,

allKurtoses=TRUE | FALSE,

allLocations=TRUE | FALSE,

allNominalStats=TRUE | FALSE,

allScales=TRUE | FALSE,

allSkewnesses=TRUE | FALSE,

alpha=double,

kurtoses=list("AVGQUANTILE", "CLASSICAL", "MOORS", "QUANTILE") | list("string-1" <, "string-2", ...>),

kurtosisAlphaQuantile=double,

kurtosisBetaQuantile=double,

locationBiweightTuning=double,

locationLowerPercentile=double,

locations=list("BIWEIGHT", "GEOMETRICMEAN", "HARMONICMEAN", "MEAN", "MEDIAN", "TRIMMEDMEAN", "WINSORIZEDMEAN") | list("string-1" <, "string-2", ...>),

locationSymmetricPercentile=double,

locationUpperPercentile=double,

maxOrder=integer,

nPercentiles=integer,

percentiles=list(double-1 <, double-2, ...>),

scaleBiweightTuning=double,

scales=list("AAD", "BIWEIGHT", "GINI", "IQR", "MAD", "STD") | list("string-1" <, "string-2", ...>),

skewnesses=list("AVGQUANTILE", "CLASSICAL", "PEARMED", "QUANTILE") | list("string-1" <, "string-2", ...>),

skewnessQuantile=double,

standardizeMoments=TRUE | FALSE

) <, list(...)>),

seed=integer,

standardError=TRUE | FALSE,

table

=list(

caslib="string",

computedOnDemand=TRUE | FALSE,

computedVars

=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>),

computedVarsProgram="string",

dataSourceOptions=list(key-1=list(any-list-or-data-type-1) <, key-2=list(any-list-or-data-type-2), ...>),

groupBy

=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>),

groupByMode="NOSORT" | "REDISTRIBUTE",

name="table-name",

onDemand=TRUE | FALSE,

orderBy

=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>),

singlePass=TRUE | FALSE,

vars

=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>),

where="where-expression",

whereTable

=list(

casLib="string"

name="table-name"

vars

=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

where="where-expression"

)

tolerance=double,

unbiased=TRUE | FALSE,

varsToArgumentsMap=list(integer-1 <, integer-2, ...>),

weight="variable-name"

)

indicates a required parameter

Summary: Input and Output Tables

If a row includes a subparameter, you can specify the name, caslib, and so on in the subparameter. Otherwise, you can specify the name, caslib, and so on in the parameter.

Parameters for Reading Input Tables
Parameter	Subparameter	Description
required parametertable	—	specifies the table name, caslib, and other common parameters.

Parameters for Creating Output Tables
Parameter	Subparameter	Description
casOutStats	—	specifies the settings for an output table.

Parameter Descriptions

casOutStats=list(casouttable)

specifies the settings for an output table.

For more information about specifying the casOutStats parameter, see the common casouttable parameter.

Alias	casOut

complementaryStats=TRUE | FALSE

when set to True, complementary univariate statistics such as uncorrected and corrected sum of squared, and coefficient of variation are computed.

Default	FALSE

confidenceInterval=TRUE | FALSE

when set to True, confidence intervals are included in the results. This parameter enables the stdErr parameter.

Default	FALSE

excessKurtosis=TRUE | FALSE

when set to True, excess kurtosis values, instead of kurtosis values, are computed. The excess kurtosis is defined with respect to the normal distribution.

Default	TRUE

freq="variable-name"

specifies the frequency variable.

Alias	frequency

includeMissingGroup=TRUE | FALSE

when set to True, missing values are allowed as group-by keys.

Default	FALSE

inputs=list( list(casinvardesc-1) <, list(casinvardesc-2), ...>)

specifies the variables to use for the analysis. You can specify a subset of the variables from the input table.

For more information about specifying the inputs parameter, see the common casinvardesc parameter.

Alias	vars

maxIterations=integer

Aliases	maxIters
Aliases	rustatsMaxNiters

nArgumentsForEachVar=list(integer-1 <, integer-2, ...>)

specifies the number of arguments (request packages) for each variable. If not set, then all request packages are included for all variables.

Alias	nArgsForEachVar

nNominalVars=integer

specifies to treat the last nNomVars variables as nominal if you do not provide a value for the nomVarsIndices parameter.

Minimum value (exclusive)	0

nominalStats=list(nominalStatistics)

computes nominal statistics. These include indices of qualitative variation and most and least frequent values.

The nominalStatistics value can be one or more of the following:

bottomK=integer

specifies the number of least frequent items to compute.

Default	5

distinctCountLimit=integer

specifies the distinct count limit.

fuzzyCompare=double

specifies the fuzzy comparison threshold that is used to determine distinctness of numeric values.

Alias	precision
Range	0–1E-05

iqv=TRUE | FALSE

when set to True, computes indices of qualitative variation. These include Shannon entropy, Gini index and a few other frequency distribution dispersion measures.

Default	TRUE

topK=integer

specifies the number of most frequent items to compute.

Default	5

nominalVarsIndices=list(integer-1 <, integer-2, ...>)

specifies the indices of the variables to treat as nominal variables.

outputTableOptions=list(outputTableOptions)

specifies options for result tables. You can specify which result tables the server returns and how group-by results are handled.

Alias	outputTableOpts

The outputTableOptions value can be one or more of the following:

forceTableReturn=TRUE | FALSE

when set to True, result tables are returned to the client even if the output is also saved as an output table.

Default	FALSE

tableNames=list("string-1" <, "string-2", ...>)

specifies the names of result tables to generate. By default, all result tables are returned.

Alias	outputTables

percentileDefinition=integer

specifies the percentile definition to use. The definitions are numbered 1 to 6. The default value is 6.

Alias	pctlDef
Default	6
Range	1–6

percentileMaxIterations=integer

specifies the maximum number of iterations for percentile computation.

Alias	pctlMaxIters

percentileTolerance=double

specifies the tolerance for percentile computation.

Alias	pctlEpsilon
Default	1E-05

quantileSketch=list(quantileSketchOptions)

specifies the options for quantile sketch.

Alias	quantileSketchOptions

The quantileSketchOptions value can be one or more of the following:

compressionFactor=double

specifies the compression factor to use for quantile sketch.

Default	10
Minimum value	1

epsilon=double

specifies the tolerance to use for quantile sketch.

Default	0.001
Range	1E-06–0.1

requestPackages=list( list(rustatsRequestPackage-1) <, list(rustatsRequestPackage-2), ...>)

specifies an array of robust univariate statistics request packages to be processed by the action.

Alias	reqPacks

The rustatsRequestPackage value can be one or more of the following:

aadLocationUseMean=TRUE | FALSE

when set to True, the mean is used, instead of the median, as the center for the absolute average deviation (AAD) scale estimator.

Alias	aadLocUseMean
Default	TRUE

allCentralizedMoments=TRUE | FALSE

when set to True, computes all centralized moments (up to the sixth order).

Default	FALSE

allKurtoses=TRUE | FALSE

when set to True, computes all kurtosis estimates.

Default	FALSE

allLocations=TRUE | FALSE

when set to True, computes all location estimates.

Default	FALSE

allNominalStats=TRUE | FALSE

computes all nominal statistics. These include indices of qualitative variation and most and least frequent values.

Default	FALSE

allScales=TRUE | FALSE

when set to True, computes all scale estimates.

Default	FALSE

allSkewnesses=TRUE | FALSE

when set to True, computes all skewness estimates.

Default	FALSE

alpha=double

specifies the significance level for the confidence interval of location estimates.

Default	0.05

kurtoses=list("AVGQUANTILE", "CLASSICAL", "MOORS", "QUANTILE") | list("string-1" <, "string-2", ...>)

specifies a list of the kurtosis estimate types to compute.

AVGQUANTILE	uses averaged quantile based skewness estimate.
CLASSICAL	uses the classical kurtosis estimate.
MOORS	uses Moor kurtosis estimate.
QUANTILE	uses quantile based kurtosis estimate.

kurtosisAlphaQuantile=double

specifies the lower (alpha) quantile for quantile or the average quantile kurtosis estimator.

Alias	kurtAlphaQuantile
Default	2.5
Range	(0–50]

kurtosisBetaQuantile=double

specifies the upper (beta) quantile for quantile or the average quantile kurtosis estimator.

Alias	kurtBetaQuantile
Default	25
Range	(0–50]

locationBiweightTuning=double

specifies the tuning factor for the Tukey biweight location estimator.

Alias	locBiweightTuning
Default	6
Minimum value (exclusive)	0

locationLowerPercentile=double

specifies the lower percentile for location estimates that need a percentile.

Alias	locLowerPerc
Default	5
Range	(0, 50)

locations=list("BIWEIGHT", "GEOMETRICMEAN", "HARMONICMEAN", "MEAN", "MEDIAN", "TRIMMEDMEAN", "WINSORIZEDMEAN") | list("string-1" <, "string-2", ...>)

specifies a list of the location estimate types to compute.

BIWEIGHT	uses Tukey biweight based estimate for location.
GEOMETRICMEAN	uses the geometric mean for location.
HARMONICMEAN	uses the harmonic mean for location.
MEAN	uses the arithmetic mean for location.
MEDIAN	uses the median value for location.
TRIMMEDMEAN	uses the trimmed mean for location. You can specify bounds with the lowerPerc, upperPerc, or symPerc parameters.
WINSORIZEDMEAN	uses the Winsorized mean for location. You can specify bounds with the lowerPerc, upperPerc, or symPerc parameters.

locationSymmetricPercentile=double

specifies the symmetric percentile for the location estimates that need percentiles. For example, a value of 20 indicates to set a lower percentile to 10 and the upper percentile to 90.

Alias	locSymPerc
Default	10
Range	(0, 100)

locationUpperPercentile=double

specifies the upper percentile for location estimates that need a percentile.

Alias	locUpperPerc
Default	95
Range	(50, 100)

maxOrder=integer

specifies the maximum order of the centralized moment to compute.

Alias	nMoments
Default	4
Maximum value	6

nPercentiles=integer

computes the equal frequency percentiles. For example, setting the value to 3 asks for the computation of 25, 50, and 75 percentiles.

Default	0
Minimum value	0

percentiles=list(double-1 <, double-2, ...>)

specifies a list of quantiles or percentiles to compute.

scaleBiweightTuning=double

specifies the tuning factor for the Tukey biweight scale estimator.

Alias	sclBiweightTuning
Default	9
Minimum value (exclusive)	0

scales=list("AAD", "BIWEIGHT", "GINI", "IQR", "MAD", "STD") | list("string-1" <, "string-2", ...>)

specifies a list of the scale estimate types to compute.

AAD	uses the absolute deviation about the mean or median as scale.
BIWEIGHT	uses Tukey biweight based estimate for scale.
GINI	uses the Gini scale for scale.
IQR	uses the inter-quartile range for scale.
MAD	uses the median absolute deviation about the median for scale.
STD	uses the standard deviation for scale.

skewnesses=list("AVGQUANTILE", "CLASSICAL", "PEARMED", "QUANTILE") | list("string-1" <, "string-2", ...>)

specifies a list of the skewness estimate types to compute.

AVGQUANTILE	uses average quantile based skewness estimate.
CLASSICAL	uses the classical skewness coefficient for skewness.
PEARMED	uses Pearson median skewness coefficient for skewness.
QUANTILE	uses quantile based skewness estimate.

skewnessQuantile=double

specifies the quantile for quantile skewness estimator.

Alias	skewQuantile
Default	25
Range	(0, 50)

standardizeMoments=TRUE | FALSE

specifies that standardized moments be generated, instead of the centralized moments.

Alias	stdMoments
Default	FALSE

seed=integer

specifies a seed value. The seed is used to generate random values.

Default	0

standardError=TRUE | FALSE

when set to True, standard errors for location are included in the results.

Alias	stdErr
Default	FALSE

* table=list(castable)

specifies the table name, caslib, and other common parameters.

For more information about specifying the table parameter, see the common castable parameter.

tolerance=double

specifies the tolerance for the iterative robust univariate statistics.

Default	1E-05

unbiased=TRUE | FALSE

when set to True, the standard deviation, variance, classical skewness and classical kurtosis are corrected for bias.

Default	TRUE

varsToArgumentsMap=list(integer-1 <, integer-2, ...>)

weight="variable-name"

specifies the weight variable.

Last updated: February 15, 2023