PLUM

PLUM is available in Statistics Base Edition.

This procedure makes use of a general class of models to allow you to analyze the relationship between a polytomous ordinal dependent variable and a set of predictors. These models utilize the ordinal nature of the dependent variable and eliminate the need for rescaling.

PLUM dependent variable [BY factor varlist] [WITH covariate varlist]

[/CRITERIA = [CIN({95** })] [DELTA({0**   })] [MXITER({100**})] [MXSTEP({5**})]
                  {value}          {value }           {n    }           {n  }
             [LCONVERGE({0**  })] [PCONVERGE({1.0E-6**})] [SINGULAR({1.0E-8**})]
                        {value}              {value   }             {value   }
             [BIAS] ]

[/LINK = {CAUCHIT}]
         {CLOGLOG}
         {LOGIT**}
         {NLOGLOG}
         {PROBIT }

[/LOCATION = [effect effect ...] ]

[/MISSING = {EXCLUDE**}]
            {INCLUDE  }

[/PRINT = [CELLINFO] [CORB] [COVB] [FIT] [HISTORY({1})] [KERNEL]
                                                  {n}
          [TPARALLEL] [PARAMETER] [SUMMARY]]

[/SAVE = [ESTPROB [(rootname [:{25**}])] [PREDCAT [(newname)]] [PCPROB [(newname)]]
                               {n   }    [ACPROB [(newname)] ]

[/SCALE = [effect effect ...] ]

[/TEST [(valuelist)] = [‘label’] effect valuelist [effect valuelist] ...;
       [effect valuelist [effect valuelist] ...;] ... ]

[/TEST [(valuelist)] = [‘label’] ALL list; [ALL list;] ... ].

** Default if the subcommand is omitted.

This command reads the active dataset and causes execution of any pending commands. See the topic Command Order for more information.

Syntax for the PLUM command can be generated from the Ordinal Regression dialog.

Example

PLUM chist.