CAS Actions FAQ

Find quick and accurate answers regarding usage, syntax, and common errors of CAS actions.

About this FAQ

Access the reference knowledge base for SAS Viya CAS actions. This technical FAQ covers syntax, parameters, and troubleshooting for common errors. Use the filters below to find code examples and optimized solutions for each specific action.

Filter by Action
2215
questions found in the knowledge base
Page 21 / 45

when set to True, uses the Misra-Gries algorithm for the frequency distribution estimation, if the distinct count limit is exceeded. Default: TRUE...
Action Sheet Read answer

specifies the nominal variables....
Action Sheet Read answer

specifies the number of shadow features to generate for each variable. Default: 5 Range: 1–20...
Action Sheet Read answer

when set to True, generates missing values at the observed missing rate. Default: TRUE...
Action Sheet Read answer

specifies the rare frequency threshold. Alias: rareFreqCutOff Minimum value (exclusive): 0...
Action Sheet Read answer

specifies the rare frequency threshold percentage. Levels whose frequencies are below the threshold are grouped together. Alias: rareThresholdPercentage Range: (0, 100)...
Action Sheet Read answer

specifies the options for sampling the shadow features The featureProbeSample value can be one or more of the following: nRecords : number of observations to sample using the specified model (astore) Alias: nObs Default: 1000 Minimum value: 1 rstore : specifies an input blob table where to read the ...
Action Sheet Read answer

specifies the CAS table to store the feature transformation and generation model. Alias: saveModel caslib : specifies the name of the caslib for the output table. indexVars : specifies the list of variables to create indexes for in the output data. lifetime : specifies the number of seconds to keep ...
Action Sheet Read answer

specifies a seed value for random number generation. This value is used for repeatable random number generation in some scenarios. Default: 0...
Action Sheet Read answer

specifies the table name, caslib, and other common parameters. caslib : specifies the caslib for the input table that you want to use with the action. By default, the active caslib is used. Specify a value only if you need to access a table from a different caslib. computedOnDemand : when set to Tru...
Action Sheet Read answer

The genmod Action fits generalized linear regression models. It provides actions for fitting linear, generalized linear, and logistic models....
Action Sheet Read answer

The alpha parameter specifies the significance level to use for the construction of all confidence intervals. The default value is 0.05, and the range is (0, 1)....
Action Sheet Read answer

When set to True, the applyRowOrder parameter uses the available groupBy and orderBy information to group and order the data. The default value is False....
Action Sheet Read answer

You can change the attributes of variables using the attributes parameter. It accepts a list of casinvardesc structures, where each structure defines attributes like format, formattedLength, label, name (required), nfd, and nfl for a variable. Attributes specified on inputs and nominals parameters a...
Action Sheet Read answer

The class parameter names the classification variables to be used as explanatory variables in the analysis. It accepts a list of classStatement structures. For more information, refer to the class Parameter section in Shared Concepts....
Action Sheet Read answer

The classGlobalOpts parameter lists options that apply to all classification variables. It accepts a classopts structure, which can include options like countMissing, descending, ignoreMissing, levelizeRaw, maxLev, order, param, ref, and split....
Action Sheet Read answer

You can suppress the display of class levels by setting the classLevelsPrint parameter to False. The default value is True....
Action Sheet Read answer

The clb parameter, when set to True, displays upper and lower confidence limits for the parameter estimates. It can also be set to 'WALD' or 'PL'....
Action Sheet Read answer

You can use the code parameter, which accepts an aircodegen structure, to write SAS DATA step code for computing predicted values of the fitted model. It can specify options like casOut (for the output table), comment, fmtWdth, indentSize, intoCutPt, iProb, labelId, lineSize, noTrim, pCatAll, and ta...
Action Sheet Read answer

The collection parameter defines a set of variables that are treated as a single effect with multiple degrees of freedom. It accepts a list of structures, each specifying 'details' (True/False), 'name' (required string), and 'vars' (required list of variable names)....
Action Sheet Read answer

The corrB parameter, when set to True, displays the correlation matrix of the parameters. The default value is False....
Action Sheet Read answer

The covB parameter, when set to True, displays the covariance matrix of the parameters. The default value is False....
Action Sheet Read answer

The display parameter specifies a list of results tables to send to the client for display. It accepts a displayTables structure with options such as caseSensitive, exclude, excludeAll, keyIsPath, names, pathType, and traceNames....
Action Sheet Read answer

When set to True, the fitData parameter specifies that the data to be scored were also used to fit the model. The default value is False....
Action Sheet Read answer

The freq parameter names the numeric variable that contains the frequency of occurrence of each observation....
Action Sheet Read answer

Input variables for analysis are specified using the inputs parameter, which accepts a list of casinvardesc structures. Each structure defines attributes like format, formattedLength, label, name (required), nfd, and nfl for a variable....
Action Sheet Read answer

The lsmeans parameter specifies the effects and subparameters for least squares means. It accepts a list of lsmeansStatement structures....
Action Sheet Read answer

The maxOptBatch parameter controls the number of observations processed in one batch. It accepts a 64-bit integer or 'AUTO'. It is related to the PAGEOBS= option in PROC GENSELECT statement....
Action Sheet Read answer

The maxResponseLevels parameter specifies the maximum number of levels allowed for a multinomial response. The default is 100, and the minimum value is 2....
Action Sheet Read answer

The model parameter names the dependent variable, explanatory effects, and model options. It accepts a genmodModel structure, which can include various options for specifying the model....
Action Sheet Read answer

The multimember parameter uses one or more classification variables specified in the vars parameter such that each observation can be associated with one or more levels of the union of the levels of the classification variables. It accepts a list of multimember structures....
Action Sheet Read answer

The nClassLevelsPrint parameter limits the display of class levels. Setting its value to 0 suppresses all levels. The minimum value is 0....
Action Sheet Read answer

When set to True, the noCheck parameter disables checking logistic models for separation. The default value is False....
Action Sheet Read answer

Nominal variables for analysis are specified using the nominals parameter, which accepts a list of casinvardesc structures. Each structure defines attributes like format, formattedLength, label, name (required), nfd, and nfl for a variable....
Action Sheet Read answer

When set to True, the normalize parameter divides the log likelihood by the total number of observations during the optimization. The default value is True....
Action Sheet Read answer

When set to True, the nostderr parameter prevents the computation of the covariance matrix and any statistic that depends on it. The default value is False....
Action Sheet Read answer

When set to True, the noxpx parameter disables the computation of X'WX and Hessian matrices, and suppresses all methods and outputs that rely on them. The default value is False....
Action Sheet Read answer

Optimization settings are configured using the optimization parameter, which accepts an optimizationStatement structure. This includes options for various convergence criteria, corrections for LBFGS, iteration limits, time limits, and the optimization technique....
Action Sheet Read answer

The output parameter creates a table on the server containing observationwise statistics after model fitting. It accepts a genmodOutputStatement structure, which includes the required casOut subparameter for specifying output table settings and various options for naming predicted values, residuals,...
Action Sheet Read answer

The parmEstLevDetails parameter specifies whether to add raw, formatted, or both raw and formatted values of classification variables to the ParameterEstimates table. Options are 'NONE', 'RAW', or 'RAW_AND_FORMATTED'. The default is 'RAW'....
Action Sheet Read answer

Data partitions by fraction are defined using the partByFrac parameter, which accepts a partByFracStatement structure. This includes a seed for random number generation, and proportions for test and validate sets (test, validate)....
Action Sheet Read answer

Data partitions by variable are defined using the partByVar parameter, which accepts a partByVarStatement structure. This includes the name (required) of the partitioning variable and values for test, train, and validate roles....
Action Sheet Read answer

When set to True, the partFit parameter displays fit statistics produced when the data are partitioned. The default value is False....
Action Sheet Read answer

The plConv parameter specifies the convergence criterion for the profile likelihood computations. The default value is 0.0001, and the range is (0, 1)....
Action Sheet Read answer

The plMaxIter parameter specifies the maximum number of iterations for the profile likelihood computations. The default value is 25, and the minimum value is 0....
Action Sheet Read answer

The plSingular parameter specifies the tolerance for testing singularity for profile likelihood computations. The range is (0, 1)....
Action Sheet Read answer

Polynomial effects are specified using the polynomial parameter, which accepts a list of polynomial structures. Each structure defines degree, details (True/False), labelStyle, mDegree, name (required), noSeparate, standardize, and vars (required list of variable names)....
Action Sheet Read answer

Repeated measures analysis options are specified using the repeated parameter, which accepts a list of genmodModelRepeated structures. This includes options for converge, corrb, corrtype, corrw, covb, depVars, ecorrb, ecovb, effects, group, maxIter, mcorrb, mcovb, mdepm, modelse, printmle, subject, ...
Action Sheet Read answer

Regression models can be restored from a binary large object (BLOB) using the restore parameter. It accepts a castable structure, which includes options for caslib, dataSourceOptions, name (required), and whereTable....
Action Sheet Read answer

Linear restrictions on parameter estimates are specified using the restrictions parameter, which accepts a list of strings representing the restrictions....
Action Sheet Read answer
Copyright © WeAreCAS 2014-2026
SAS and all other SAS Institute Inc. product or service names are registered trademarks or trademarks of SAS Institute Inc. in the USA and other countries. ® indicates USA registration. WeAreCAS is an independent community site and is not affiliated with SAS Institute Inc.